v0.1.0 - Initial Release

Initial release of DPBench - A benchmark framework for evaluating LLM multi-agent coordination under resource contention.

Features

• Simultaneous and sequential decision modes
• Configurable agent counts (N philosophers)
• Optional inter-agent communication
• Comprehensive metrics: deadlock rate, throughput, fairness, starvation
• JSONL logging and human-readable transcripts
• Works with any LLM via simple function protocol