Run

Funktionen

• One-shot execution of init → baseline → spawn → eval → merge
• Supports custom agent templates
• Configurable evaluation metrics and directions
• User confirmation for merge step
• Parallel agent spawning

Anwendungsfälle

• Automating repetitive agent development cycles.
• Ensuring consistent agent evaluation and merging processes.
• Reducing the complexity of managing multi-agent workflows.
• Quickly iterating on agent performance with a single command.

Nicht-Ziele

• Performing individual lifecycle steps in isolation.
• Replacing the detailed configuration of individual AgentHub commands.
• Handling agent failures beyond stopping the workflow and reporting errors.

Workflow

1. Initialize the agent session with provided parameters.
2. Capture a baseline metric if an evaluation command is supplied.
3. Spawn agents in parallel, optionally using a specified template.
4. Monitor agent completion and display summaries.
5. Evaluate results based on metrics or LLM judge mode.
6. Confirm merge with the user before executing the merge command.