Metadata-Version: 2.4
Name: build-agent-earnings-optimizer-v4
Version: 1.0.0
Summary: Build: Agent Earnings Optimizer v4
License: MIT
Project-URL: Homepage, https://github.com/worksOnMyFridge/build-agent-earnings-optimizer-v4
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: aiohttp>=3.9
Requires-Dist: requests>=2.31

# build-agent-earnings-optimizer-v4

Analyzes agent performance and suggests optimizations to maximize earnings.

**Python 3.9+**

## Installation

pip install build-agent-earnings-optimizer-v4

## Quick Start

from build_agent_earnings_optimizer_v4 import AgentStats

stats = AgentStats(
    win_rate=0.65,
    avg_earnings=120.0,
    response_time_hours=2.5,
    quality_score=4.2,
    job_types={"design": 0.6, "writing": 0.4},
    total_bids=80,
    total_wins=52,
)

## API Reference

### `AgentStats`

Container for agent performance statistics.

| Parameter | Type | Description |
|---|---|---|
| `win_rate` | `float` | Ratio of won bids |
| `avg_earnings` | `float` | Average earnings per job |
| `response_time_hours` | `float` | Average response time |
| `quality_score` | `float` | Quality rating (default `0.0`) |
| `job_types` | `dict[str, float]` | Job type distribution |
| `total_bids` | `int` | Total bids submitted |
| `total_wins` | `int` | Total bids won |

### Methods

| Method | Description |
|---|---|
| `render()` | Render a visual summary of agent stats |
| `add_peer(peer)` | Add a peer agent for benchmarking |
| `record_history(entry)` | Record a historical performance entry |
| `analyze()` | Run optimization analysis and return an `OptimizationReport` |
| `track_progress()` | Track progress toward earnings goals |

## Data Classes

- **`Recommendation`** — Single optimization recommendation with projected impact
- **`OptimizationReport`** — Full report containing stats and recommendations

## License

MIT
