autourgos-agent-utils 0.1.0

Shared utilities for Autourgos agents — colored logger, tool executor, and history tracking.

Autourgos Agent Utils

Essential, reusable utilities for building and managing AI agents in the Autourgos ecosystem.

---

Welcome to the autourgos-agent-utils package. This library provides comprehensive, high-performance utilities for colored console logging, dynamic tool execution, structured conversation history tracking, and managing context-windowed scratchpads.

Built to simplify agent infrastructure, it abstracts away the complex boilerplate of tool invocation and state tracking so you can focus on building intelligent agent logic.

---

Table of Contents

1. Installation
2. Agent Logging
3. Tool Execution
4. Memory & History
   • AgentHistoryLogger
5. Helper Functions

---

Installation

Install the utility package using pip:

pip install autourgos-agent-utils

Note: This package depends on autourgos-core >= 0.1.0.

---

Agent Logging

AgentLogger provides enhanced, colored console logging tailored specifically for agent workflows (Thoughts, Actions, Observations, Final Answers).

from autourgos_agent_utils import create_logger

# Initialize a colored logger for a specific agent
logger = create_logger("MyAgent")

logger.info("Agent initialized successfully.")
logger.warning("Approaching token limits.")

---

Tool Execution

Robust dynamic tool execution components (Tool_Executor and AsyncTool_Executor) safely invoke external functions and tools, automatically handling parameter injection and error recovery.

from autourgos_agent_utils import Tool_Executor, register_tool

@register_tool
def get_weather(location: str) -> str:
    """Fetches the weather for a given location."""
    return f"The weather in {location} is sunny."

tools = [get_weather]
executor = Tool_Executor(tools)

# Dynamically execute a tool by name with dictionary arguments
result = executor.execute("get_weather", {"location": "London"})
print(result) # Output: The weather in London is sunny.

---

Memory & History

AgentHistoryLogger

Keep track of conversational trails and reasoning steps with markdown-based history export.

from autourgos_agent_utils import AgentHistoryLogger

history = AgentHistoryLogger(agent_name="ResearchBot", enabled=True)
history.start_task("I need to find the latest documentation.")
history.log_iteration(
    iteration_num=1,
    thought="I should search for the latest documentation.",
    tools=[{"tool": "search_web", "params": {"query": "autourgos docs"}}],
    observations=[{"tool": "search_web", "result": "Found 5 documents."}]
)
history.log_final("Here are the latest docs.")

---

Helper Functions

The package exposes various utility functions for common agent tasks:

• parse_json_object: Safely extracts and parses JSON strings embedded deep within raw LLM text responses.
• check_timeout: Evaluates elapsed execution time against configured limits.
• escape_prompt_braces: Prevents KeyError exceptions when utilizing .format() on prompts containing raw JSON structures.

---

Made with ❤️ by DevxJitin and Sonia