Attributes

The Agent system is configured through the Agent class, which provides the following attributes:

Attribute	Type	Default	Description
`model`	str \| Model	`"openai/gpt-4o"`	Model identifier or Model instance
`name`	str \| None	`None`	Agent name for identification
`agent_id_`	str \| None	`None`	Unique identifier for the agent instance
`memory`	Memory \| None	`None`	Memory instance for conversation history
`db`	DatabaseBase \| None	`None`	Database instance (overrides memory if provided)
`debug`	bool	`False`	Enable debug logging
`company_url`	str \| None	`None`	Company URL for context
`company_objective`	str \| None	`None`	Company objective for context
`company_description`	str \| None	`None`	Company description for context
`company_name`	str \| None	`None`	Company name for context
`system_prompt`	str \| None	`None`	Custom system prompt
`reflection`	bool	`False`	Enable reflection capabilities
`compression_strategy`	str	`"none"`	Context compression method: ‘none’, ‘simple’, ‘llmlingua’
`compression_settings`	Dict \| None	`None`	Settings for compression strategy
`reliability_layer`	Any \| None	`None`	Reliability layer for robustness
`canvas`	Canvas \| None	`None`	Canvas instance for visual interactions
`retry`	int	`1`	Number of retry attempts
`mode`	str	`"raise"`	Retry mode behavior: ‘raise’ or ‘return_false’
`role`	str \| None	`None`	Agent role
`goal`	str \| None	`None`	Agent goal
`instructions`	str \| None	`None`	Specific instructions
`education`	str \| None	`None`	Agent education background
`work_experience`	str \| None	`None`	Agent work experience
`feed_tool_call_results`	bool	`False`	Include tool results in memory
`show_tool_calls`	bool	`True`	Display tool calls
`tool_call_limit`	int	`5`	Maximum tool calls per execution
`enable_thinking_tool`	bool	`False`	Enable orchestrated thinking
`enable_reasoning_tool`	bool	`False`	Enable reasoning capabilities
`user_policy`	Policy \| List[Policy] \| None	`None`	User input safety policy
`agent_policy`	Policy \| List[Policy] \| None	`None`	Agent output safety policy
`settings`	ModelSettings \| None	`None`	Model-specific settings
`profile`	ModelProfile \| None	`None`	Model profile configuration
`reflection_config`	ReflectionConfig \| None	`None`	Configuration for reflection
`reasoning_effort`	str \| None	`None`	Reasoning effort: ‘low’, ‘medium’, ‘high’ (OpenAI)
`reasoning_summary`	str \| None	`None`	Reasoning summary: ‘concise’, ‘detailed’ (OpenAI)
`thinking_enabled`	bool \| None	`None`	Enable thinking (Anthropic/Google)
`thinking_budget`	int \| None	`None`	Token budget for thinking
`thinking_include_thoughts`	bool \| None	`None`	Include thoughts in output (Google)
`reasoning_format`	str \| None	`None`	Reasoning format: ‘hidden’, ‘raw’, ‘parsed’ (Groq)

Configuration Example

from upsonic import Agent, Task
from upsonic.storage.providers.sqlite import SqliteStorage
from upsonic import Memory

# Create storage and memory
storage = SqliteStorage("sessions", "profiles", "agent_memory.db")
memory = Memory(
    storage=storage,
    session_id="session_001",
    user_id="user_001",
    full_session_memory=True,
    summary_memory=True,
    model="openai/gpt-4o-mini"
)

# Create agent with configuration
agent = Agent(
    model="openai/gpt-4o",
    name="Assistant",
    memory=memory,
    debug=True,
    role="AI Assistant",
    goal="Help users with their questions",
    show_tool_calls=True,
    tool_call_limit=10
)

# Execute a task
task = Task("Hello! What can you help me with?")
result = agent.do(task)
print(result)

GET STARTED

CONCEPTS

STARTING AN AGENT PROJECT

DEPLOYMENT

FURTHER READINGS

Attributes

Attributes

Configuration Example

GET STARTED

CONCEPTS

STARTING AN AGENT PROJECT

DEPLOYMENT

FURTHER READINGS

​Attributes

​Configuration Example

Attributes

Configuration Example