• Added the swarm's queen bee to the /swarm board header and a 🐝 beside each live member in the Roster; in terminals with Kitty graphics, such as Kitty and Ghostty, each member gets its own colored bee card that flaps while that member is working, and other terminals, including tmux, show the queen as pixel art when the window is at least 60×35.
• Added a continuation_active field to the JSON input of Stop hooks, which is true while the agent is already working on a continuation an earlier Stop hook requested, so a hook such as "run the tests before finishing" can tell it has already asked and avoid looping.
• Added a supportsThoughtCirculation option to admin-managed model entries (models.list[] in admin settings), so organizations can let non-Gemini models behind an enterprise model gateway reuse their reasoning from earlier turns; when it is unset, the model's default applies.
• Improved Auto mode's review of commands that would leave the terminal sandbox so it asks less often on safe reads: GitHub API reads, fetches into an existing clone, and single-file downloads such as raw.githubusercontent.com URLs no longer get the repository popularity, age, and release checks that cloning a repository still gets, host names that start with a digit are no longer mistaken for IP addresses, and reading ~/.ssh/config, known_hosts, authorized_keys, or public keys (*.pub) is no longer treated as reading secrets, while private keys still are and sending any .ssh file elsewhere is still blocked.
• Improved agy plugin validate to warn when a plugin hook command uses ${PLUGIN_ROOT} or $PLUGIN_ROOT, which older CLI versions do not set, and to suggest a relative path instead, since hooks already run in the plugin's folder; the warning fails validation only with --strict.
• Changed pay-as-you-go Google Cloud accounts that sign in with Application Default Credentials (AGY_ADC_AUTH) to use the same permission settings as other pay-as-you-go accounts, which makes Auto mode available to them; Gemini Enterprise accounts keep following their organization's admin-controlled permission settings, including their unsandboxed(...) deny and ask rules, and are not offered Auto mode.
• Fixed undo and redo in the prompt, including u in Vim mode, moving the cursor to the end of the input; the cursor now returns to where the undone or redone edit was made.
• Fixed agy plugin install ignoring the skill folders that a Claude Code plugin lists in the "skills" field of its manifest; those skills are now installed and loaded, and the install summary warns about listed paths that are missing, contain no skill, or point outside the plugin.
• Fixed agy plugin install and agy plugin import leaving a half-copied plugin that still loaded as enabled when an install failed partway; installs are now swapped in all at once and the previous version is restored on failure, plugins containing symlinks that point outside the plugin, FIFOs, or device files are refused, and a command whose file name cannot be used as a skill folder name is skipped with a warning instead of failing the import.
• Fixed pressing esc in a swarm member's conversation opened from /swarm board with o dropping you back at the prompt; it now returns to the board with the same selection, filter, focused pane, and zoom.
• Fixed a swarm coordinator sometimes ending its turn with a one-line filler reply instead of its real answer after being sent back to re-read board posts it had already read, fixed a coordinator offering a sidecar:// board link that the CLI cannot open instead of /swarm board on later turns of a swarm, and fixed agy -p runs that start a swarm pointing you to /swarm board, which headless runs cannot open.
• Fixed some models served through an enterprise model gateway being sent requests without native tool declarations, which kept the agent from calling tools reliably; every model in the gateway's catalog, including models listed in AGY_LLM_GATEWAY_MODELS, now gets native tool calls.
• Fixed custom Gemini models served through an enterprise model gateway or an admin model list, such as tuned models, cutting off long edits and file writes at 8,192 output tokens; they now default to the same 65,535-token output limit as built-in Gemini models, and an explicit admin maxOutputTokens value still takes precedence.
• Fixed duplicate approval prompts and sandbox errors for organizations that enforce sandbox mode on machines without an OS sandbox, such as some Windows hosts or Linux with user namespaces disabled; commands now ask for review once and then run.
• Fixed editing project rules with /permissions clearing the marker that records the project's permission rules as already migrated, which made the Antigravity app migrate them again and could drop command(...) allow rules when the sandbox is on.