xpander-sdk 2.0.152__tar.gz → 2.0.154__tar.gz

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xpander-sdk
-Version: 2.0.152
+Version: 2.0.154
 Summary: xpander.ai Backend-as-a-service for AI Agents - SDK
 Home-page: https://www.xpander.ai
 Author: xpanderAI
@@ -417,6 +417,93 @@ load_dotenv()
 config = Configuration()
 ```
 
+## 🏢 Self-Hosted Deployment
+
+If you're using a self-hosted xpander.ai deployment, configure the SDK to point to your Agent Controller endpoint.
+
+**Important**: Use the **Agent Controller API key** generated during Helm installation, not your xpander.ai cloud API key.
+
+### Configuration
+
+```bash
+# Set environment variables
+export XPANDER_API_KEY="your-agent-controller-api-key"  # From Helm installation
+export XPANDER_ORGANIZATION_ID="your-org-id"
+export XPANDER_BASE_URL="https://agent-controller.my-company.com"
+```
+
+Or configure explicitly:
+
+```python
+from xpander_sdk import Configuration
+
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+```
+
+### Using with Agno Framework
+
+```python
+from xpander_sdk import Backend, Configuration
+from agno.agent import Agent
+
+# Configure for self-hosted
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+
+# Initialize Backend with self-hosted config
+backend = Backend(configuration=config)
+
+# Create agent - it will use your self-hosted infrastructure
+agno_agent = Agent(**backend.get_args(agent_id="agent-123"))
+
+# Run agent
+result = await agno_agent.arun(
+    input="What can you help me with?",
+    stream=True
+)
+```
+
+### Complete Self-Hosted Example
+
+```python
+import asyncio
+from xpander_sdk import Configuration, Agent
+
+async def main():
+    # Configure for self-hosted deployment
+    config = Configuration(
+        api_key="your-agent-controller-api-key",  # From Helm installation
+        organization_id="your-org-id",
+        base_url="https://agent-controller.my-company.com"
+    )
+    
+    # Load agent from self-hosted deployment
+    agent = await Agent.aload("agent-123", configuration=config)
+    print(f"Agent: {agent.name}")
+    
+    # Create and execute task
+    task = await agent.acreate_task(
+        prompt="Analyze Q4 sales data",
+        file_urls=["https://example.com/sales-q4.csv"]
+    )
+    print(f"Task created: {task.id}")
+    print(f"Status: {task.status}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+**Important**: Make sure your `base_url` points to the Agent Controller endpoint (e.g., `https://agent-controller.{your-domain}`), not the root domain.
+
+📖 **Full Guide**: [Self-Hosted Configuration Documentation](https://docs.xpander.ai/api-reference/configuration/self-hosted)
+
 ## 🔄 Error Handling
 
 ```python

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/README.md

@@ -368,6 +368,93 @@ load_dotenv()
 config = Configuration()
 ```
 
+## 🏢 Self-Hosted Deployment
+
+If you're using a self-hosted xpander.ai deployment, configure the SDK to point to your Agent Controller endpoint.
+
+**Important**: Use the **Agent Controller API key** generated during Helm installation, not your xpander.ai cloud API key.
+
+### Configuration
+
+```bash
+# Set environment variables
+export XPANDER_API_KEY="your-agent-controller-api-key"  # From Helm installation
+export XPANDER_ORGANIZATION_ID="your-org-id"
+export XPANDER_BASE_URL="https://agent-controller.my-company.com"
+```
+
+Or configure explicitly:
+
+```python
+from xpander_sdk import Configuration
+
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+```
+
+### Using with Agno Framework
+
+```python
+from xpander_sdk import Backend, Configuration
+from agno.agent import Agent
+
+# Configure for self-hosted
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+
+# Initialize Backend with self-hosted config
+backend = Backend(configuration=config)
+
+# Create agent - it will use your self-hosted infrastructure
+agno_agent = Agent(**backend.get_args(agent_id="agent-123"))
+
+# Run agent
+result = await agno_agent.arun(
+    input="What can you help me with?",
+    stream=True
+)
+```
+
+### Complete Self-Hosted Example
+
+```python
+import asyncio
+from xpander_sdk import Configuration, Agent
+
+async def main():
+    # Configure for self-hosted deployment
+    config = Configuration(
+        api_key="your-agent-controller-api-key",  # From Helm installation
+        organization_id="your-org-id",
+        base_url="https://agent-controller.my-company.com"
+    )
+    
+    # Load agent from self-hosted deployment
+    agent = await Agent.aload("agent-123", configuration=config)
+    print(f"Agent: {agent.name}")
+    
+    # Create and execute task
+    task = await agent.acreate_task(
+        prompt="Analyze Q4 sales data",
+        file_urls=["https://example.com/sales-q4.csv"]
+    )
+    print(f"Task created: {task.id}")
+    print(f"Status: {task.status}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+**Important**: Make sure your `base_url` points to the Agent Controller endpoint (e.g., `https://agent-controller.{your-domain}`), not the root domain.
+
+📖 **Full Guide**: [Self-Hosted Configuration Documentation](https://docs.xpander.ai/api-reference/configuration/self-hosted)
+
 ## 🔄 Error Handling
 
 ```python

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="xpander-sdk",
-    version="2.0.152",
+    version="2.0.154",
     author="xpanderAI",
     author_email="dev@xpander.ai",
     description="xpander.ai Backend-as-a-service for AI Agents - SDK",

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/src/xpander_sdk/modules/agents/models/agent.py

@@ -383,7 +383,10 @@ class AgentGraphItem(BaseModel):
     llm_settings: Optional[List[AgentGraphItemLLMSettings]] = []
     is_first: Optional[bool] = False
 
-
+class LLMReasoningEffort(str, Enum):
+    Low = "low"
+    Medium = "medium"
+    High = "high"
 
 class AIAgentConnectivityDetailsA2AAuthType(str, Enum):
     NoAuth = "none"

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/src/xpander_sdk/modules/agents/sub_modules/agent.py

@@ -40,6 +40,7 @@ from xpander_sdk.modules.agents.models.agent import (
     AgentType,
     DatabaseConnectionString,
     LLMCredentials,
+    LLMReasoningEffort,
 )
 from xpander_sdk.modules.agents.models.knowledge_bases import AgentKnowledgeBase
 from xpander_sdk.modules.knowledge_bases.knowledge_bases_module import KnowledgeBases
@@ -151,6 +152,7 @@ class Agent(XPanderSharedModel):
             using_nemo: Optional[bool]
             model_provider: str
             model_name: str
+            llm_reasoning_effort: Optional[LLMReasoningEffort] = LLMReasoningEffort.Medium
             llm_api_base: Optional[str]
             webhook_url: Optional[str]
             created_at: Optional[datetime]
@@ -192,6 +194,7 @@ class Agent(XPanderSharedModel):
     using_nemo: Optional[bool] = False
     model_provider: str
     model_name: str
+    llm_reasoning_effort: Optional[LLMReasoningEffort] = LLMReasoningEffort.Medium
     llm_api_base: Optional[str] = None
     webhook_url: Optional[str] = None
     created_at: Optional[datetime] = None

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/src/xpander_sdk/modules/backend/frameworks/agno.py

@@ -8,7 +8,7 @@ from loguru import logger
 from xpander_sdk import Configuration
 from xpander_sdk.models.shared import OutputFormat, ThinkMode
 from xpander_sdk.modules.agents.agents_module import Agents
-from xpander_sdk.modules.agents.models.agent import AgentGraphItemType
+from xpander_sdk.modules.agents.models.agent import AgentGraphItemType, LLMReasoningEffort
 from xpander_sdk.modules.agents.sub_modules.agent import Agent
 from xpander_sdk.modules.backend.utils.mcp_oauth import authenticate_mcp_server
 from xpander_sdk.modules.tasks.sub_modules.task import Task
@@ -278,6 +278,10 @@ def _load_llm_model(agent: Agent, override: Optional[Dict[str, Any]]) -> Any:
             return env_llm_key or agent.llm_credentials.value
 
     llm_args = {}
+    
+    if agent.llm_reasoning_effort and agent.llm_reasoning_effort != LLMReasoningEffort.Medium:
+        llm_args = { "reasoning_effort": agent.llm_reasoning_effort.value }
+    
     if agent.llm_api_base and len(agent.llm_api_base) != 0:
         llm_args["base_url"] = agent.llm_api_base
     

{xpander_sdk-2.0.152 → xpander_sdk-2.0.154}/src/xpander_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xpander-sdk
-Version: 2.0.152
+Version: 2.0.154
 Summary: xpander.ai Backend-as-a-service for AI Agents - SDK
 Home-page: https://www.xpander.ai
 Author: xpanderAI
@@ -417,6 +417,93 @@ load_dotenv()
 config = Configuration()
 ```
 
+## 🏢 Self-Hosted Deployment
+
+If you're using a self-hosted xpander.ai deployment, configure the SDK to point to your Agent Controller endpoint.
+
+**Important**: Use the **Agent Controller API key** generated during Helm installation, not your xpander.ai cloud API key.
+
+### Configuration
+
+```bash
+# Set environment variables
+export XPANDER_API_KEY="your-agent-controller-api-key"  # From Helm installation
+export XPANDER_ORGANIZATION_ID="your-org-id"
+export XPANDER_BASE_URL="https://agent-controller.my-company.com"
+```
+
+Or configure explicitly:
+
+```python
+from xpander_sdk import Configuration
+
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+```
+
+### Using with Agno Framework
+
+```python
+from xpander_sdk import Backend, Configuration
+from agno.agent import Agent
+
+# Configure for self-hosted
+config = Configuration(
+    api_key="your-agent-controller-api-key",  # From Helm installation
+    organization_id="your-org-id",
+    base_url="https://agent-controller.my-company.com"
+)
+
+# Initialize Backend with self-hosted config
+backend = Backend(configuration=config)
+
+# Create agent - it will use your self-hosted infrastructure
+agno_agent = Agent(**backend.get_args(agent_id="agent-123"))
+
+# Run agent
+result = await agno_agent.arun(
+    input="What can you help me with?",
+    stream=True
+)
+```
+
+### Complete Self-Hosted Example
+
+```python
+import asyncio
+from xpander_sdk import Configuration, Agent
+
+async def main():
+    # Configure for self-hosted deployment
+    config = Configuration(
+        api_key="your-agent-controller-api-key",  # From Helm installation
+        organization_id="your-org-id",
+        base_url="https://agent-controller.my-company.com"
+    )
+    
+    # Load agent from self-hosted deployment
+    agent = await Agent.aload("agent-123", configuration=config)
+    print(f"Agent: {agent.name}")
+    
+    # Create and execute task
+    task = await agent.acreate_task(
+        prompt="Analyze Q4 sales data",
+        file_urls=["https://example.com/sales-q4.csv"]
+    )
+    print(f"Task created: {task.id}")
+    print(f"Status: {task.status}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+**Important**: Make sure your `base_url` points to the Agent Controller endpoint (e.g., `https://agent-controller.{your-domain}`), not the root domain.
+
+📖 **Full Guide**: [Self-Hosted Configuration Documentation](https://docs.xpander.ai/api-reference/configuration/self-hosted)
+
 ## 🔄 Error Handling
 
 ```python