Auto-compact on idle, aligned to the model's prompt cache TTL

Describe the feature or problem you'd like to solve

Prompt cache TTL is ~5 min. After an idle gap the next turn re-reads the full context uncached, at a cost and latency that scale with context size. Compaction only triggers on token thresholds today (#1688, #2333), so the only workaround is running /compact manually before going idle.

Proposed solution

A time-based compaction trigger, with the idle threshold tied to the active model's cache TTL.

Example prompts or workflows

No response

Additional context

No response

首先跟踪现有的 token 阈值压缩流程，以及活动模型的 prompt cache TTL 在哪里可用。围绕该 TTL 定义空闲触发条件，然后验证空闲间隔后的下一轮是否使用压缩后的上下文，而不是重新读取完整的未缓存上下文。