2 Commits

Author SHA1 Message Date
YeonGyu-Kim
3d273ff853 fix(hooks): use last assistant message tokens instead of cumulative sum
Previously, token calculation accumulated ALL assistant messages' tokens,
causing incorrect usage display (e.g., 524.9%) after compaction.
Now uses only the last message's input tokens, which reflects the actual
current context window usage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-13 01:02:21 +09:00
YeonGyu-Kim
341e5a959d feat(hooks): add grep-output-truncator for context-aware output limiting 2025-12-06 10:54:22 +09:00