Harness — Long-Running Agent Framework Executable protocol enabling any agent task to run continuously across multiple sessions with automatic progress recovery, task dependency resolution, failure rollback, and standardized error handling. Design Principles 1. Design for the agent, not the human — Test output, docs, and task structure are the agent's primary interface 2. Progress files ARE the context — When context window resets, progress files + git history = full recovery 3. Premature completion is the #1 failure mode — Structured task lists with explicit completion criteria prevent decla…