v1.0.14
stablePublished Aug 31, 2026
NEW15BREAKING8PERF2FIX1
Trailer
Changelog
1.0.14 — 2026-08-31
Features
- OIDC token refresh is now proactive by default for better reliability.
- PostToolUse hooks can now provide feedback and context to the model after tool execution.
- SDK-registered PostToolUse hooks now provide model-facing feedback.
- grok usage <session-id> now shows persisted per-turn token and cost data.
- Retry status in composer and title now shows a short reason for the retry.
- Models can now declare a different identifier for each reasoning-effort level instead of always sending the same id.
- Prompt suggestions now respect remote configuration and default to the current session model.
- Windows CLI downloads are now ~70% smaller using the same compressed sidecars as macOS and Linux.
Bug Fixes
- grok inspect now correctly shows Claude bypass locks as advisory rather than enforced.
- Subagent sessions no longer leak threads or file descriptors when the parent is busy.
- Cold startup no longer performs duplicate remote settings fetches.
- Compaction failures due to context size now degrade input instead of retrying identically.
- --sandbox strict now restricts writes to ~/.grok/sessions only.
- Subagent spawning now waits longer on a busy coordinator and shows clearer retry guidance instead of "unreachable".
- Failed task and todo tool calls now appear in the transcript instead of disappearing without a trace.
- Composer status row no longer collapses or flashes when using double-Enter to send now.
- Session close is no longer delayed by a single slow hook; each SessionEnd hook now has its own timeout.
- Hook removal in the extensions modal no longer offers actions that the handler will refuse.
- Interjections during a turn are now delivered atomically or not at all.
- Subagent tasks no longer get incorrectly cancelled when the parent session is waiting for completion.
- Workflow detail view now closes the overlay on X or outside click instead of returning to the run list.
- Resuming subagents now succeeds for larger transcripts that still fit the model context with headroom.
Performance
- Startup now fetches remote settings only once per boot instead of potentially twice.
- First message on large repositories no longer waits on repository status scan.
- Large session memory no longer blocks the agent during turn completion or subagent spawning.
- Signed-in CLI starts faster by serving remote settings from a local cache on warm boots.