grok-build-upstream-mirror/crates/codegen/xai-grok-shell/changelogs/0.2.107.md

# 0.2.107 — 2026-07-20

## Features

- **Stop hooks** can now keep the agent running by feeding feedback back to the model instead of ending the turn.
- **Custom models** can now authenticate using rotating tokens fetched from a command, similar to credential helpers.
- **Feedback** now includes author details when provided, helping with follow-up.
- **Sessions** can now resume across hosts by mirroring transcripts to external storage like S3.
- **Sessions** can now be imported and resumed from mirrored state across hosts.
- **Auto mode** now continues after classifier blocks by telling the agent the reason, escalating only after repeated denials.
- **Session storage** can now flush after every frame (eager mode) instead of only at turn end.

## Bug Fixes

- **Ctrl+B** now backgrounds running commands; **Ctrl+G** toggles the tasks pane.
- **OAuth popups** in live preview now redirect correctly after login.
- **Git status** shown to the model at startup now includes unstaged and untracked files.
- **Tool descriptions** now stay correct when parameter names are randomized.
- **Minimal mode** now shows full reasoning in scrollback and collapses successful lookup results to one-line headers.
- **Empty commands** like `true` or bare `echo` now remind the model to stop and wait for background work instead of spinning.

## Performance

- **Recap summaries** after idle now load much faster by reusing the previous turn's cached context.
Synced from monorepo Synced from monorepo Changes: - Shell: accept target response id on rewind execute - Shell: stamp response id on chat user message chunks - Worktree: optional rebuild and stale git registration cleanup in auto-GC - Worktree: kind-aware auto-GC TTLs and config knobs - Worktree: macOS process CWD scan and Unix PID liveness for GC guards - Worktree: automatic throttled GC on startup (Linux age-based; non-Linux dead-only) - Pager: add `[ui].combine_queued_prompts` to batch queued follow-ups - Shell: stop overwriting user skills - Tools: read markdown in `skills/` directories untruncated - `/usage` shows per-session token and dollar usage in the TUI - Security: prompt on environment-dumping `ps` variants - Security: always-safe `kubectl` no longer runs arbitrary kubeconfig credential plugins without permission - Tools: make scheduler deletion durable - Shell: add relocation storage primitives - Shell: give side model calls their own conversation ids - Fix five workflow-runtime bugs (budget, pause, cancel, reconnect) - Security: peel `env -S` / `--split-string` operands in the Bash permission gate (managed deny/ask) - Pager: expose doctor in the TUI - Security: block unauthorized RCE via abused safe commands - Pager idle watcher cue: "1 subagent still running" instead of "watching · 1 subagent" - Security: block `rg --pre` arbitrary code execution in auto-mode - Voice: diagnose silent-mic failures (macOS permission) and add doctor/terminal-setup Voice section - App builder deployer: `allow_forking` and `show_built_with_grok` - Pager: stop stacking duplicate "Worked for" markers on parked turns - Shell: support `max` as a distinct reasoning effort tier - Tools: serialize background `/loop` fires on the whole work unit - Shell: add working-directory relocation state primitives - Proto: `ClientToolResult` and `ChatConfig` client-side tools - Shell: model providers - Chat: select App Builder product on the Build path - Shell: attach author identity to feedback when the deployment opts in - Doctor: fix for SSH wrap setup - Workflow authoring skills: create-workflow and import-claude-workflow docs - Add read-only grok doctor - Sandbox: apply Landlock without a controlling TTY - Pager: recover image paste over grok wrap on headless remotes - Pager: make actions screen-mode aware - Shell: resume sessions when the working directory moves - Pager: centralize terminal diagnostics - Workspace: gate inline shell file access - Pager: centralize terminal probes - Pager: edit minimal prompts in an external editor - Pager: standardize backgrounding on Ctrl+B - Shell: recap rides the parent turn's prompt cache - Tools: add scheduler lifecycle version clock Source-Revision: 0f4d7c91b8b2b408333f6de1e8a76cb8eaa71899 2026-07-21 18:10:23 +00:00			`# 0.2.107 — 2026-07-20`

			`## Features`

			`- Stop hooks can now keep the agent running by feeding feedback back to the model instead of ending the turn.`
			`- Custom models can now authenticate using rotating tokens fetched from a command, similar to credential helpers.`
			`- Feedback now includes author details when provided, helping with follow-up.`
			`- Sessions can now resume across hosts by mirroring transcripts to external storage like S3.`
			`- Sessions can now be imported and resumed from mirrored state across hosts.`
			`- Auto mode now continues after classifier blocks by telling the agent the reason, escalating only after repeated denials.`
			`- Session storage can now flush after every frame (eager mode) instead of only at turn end.`

			`## Bug Fixes`

			`- Ctrl+B now backgrounds running commands; Ctrl+G toggles the tasks pane.`
			`- OAuth popups in live preview now redirect correctly after login.`
			`- Git status shown to the model at startup now includes unstaged and untracked files.`
			`- Tool descriptions now stay correct when parameter names are randomized.`
			`- Minimal mode now shows full reasoning in scrollback and collapses successful lookup results to one-line headers.`
			- Empty commands like `true` or bare `echo` now remind the model to stop and wait for background work instead of spinning.

			`## Performance`

			`- Recap summaries after idle now load much faster by reusing the previous turn's cached context.`