continuity-log

What problem does it solve?

Continuity-log solves the problem of losing high-value decisions and resume context during long, multi-turn, or compaction-heavy agent runs, which otherwise leads to repeated analysis and wasted cycles.

Core Features & Use Cases

• Compact-safe decision packets: Store outcomes of reasoning (decisions, evidence, rejected alternatives) instead of raw hidden chain-of-thought.
• Clear resume points: Record where the next turn should continue after interruptions, handoffs, or context compaction.
• Blockers, risks, and open questions: Preserve what is known, what is uncertain, and what must be revisited.
• Anti-duplication for future turns: Prevent re-running the same analysis by keeping load-bearing decisions and their justification.
• Use case: When an agent pauses due to time or context limits, the next run can quickly reconstruct the operational path without repeating the same reasoning.

Quick Start

Write a timestamped continuity entry capturing the objective, decision, evidence, rejected alternatives, and the exact resume point to the most appropriate continuity location for your run.