Antigravity 1.2.8: Long prompts stay intact as context compaction shares

Release notes

FEATURE

Long prompts stay intact as context compaction shares budgets across turns

After dozens of back-and-forth turns, does the AI still remember the long brief you started with? Previously, compaction enforced a rigid length cap on every captured user prompt, lopping off details from a long initial prompt even when all subsequent follow-up turns were brief. The user-request budget is now shared flexibly across all captured prompts, preserving the full context of long instructions whenever later prompts are short. Summary and truncation budgets are also now calculated from the model's full context window rather than the narrower compaction trigger threshold, ensuring compacted summaries and background-task lists are never cut short prematurely.

BUGFIX

Custom models support PDFs and stop throwing unsupported mime type errors

Added a custom model in settings.json and got unsupported mime type the moment you sent a PDF or audio? Previously, attaching these media files or having tools emit audio and document outputs would fail outright. Custom models now accept PDFs by default and strictly honor the modelFeatures media flags for images, video, PDF, and audio, allowing media files to pass to the model as configured.

BUGFIX

Pressing Ctrl+G to open Vim no longer hangs when editing prompts

When you want to compose prompts comfortably in the terminal, pressing Ctrl+G jumps into a full-screen editor like vim. Previously, pressing this shortcut could freeze the editor with a Vim: Warning: Output is not to a terminal warning because its output was not connected to a real terminal. External editors now run against a real terminal stdout, so pressing Ctrl+G opens your editor immediately and returns you to the conversation as soon as you save and exit.

BUGFIX

Voice dictation no longer erases drafts on timeout and auto-finalizes at 3.5 minutes

Talked into the mic at length, only to end up with nothing? Previously, recordings exceeding 4 minutes triggered a deadline error and failed completely, discarding the entire drafted transcript. Recordings now automatically stop and finalize at 3 minutes 30 seconds, reliably converting your spoken words into text so you never lose your progress.

BUGFIX

Personal sign-ins no longer see a Google Cloud Project ID

Signed in with a personal account and saw a cryptic cloud project ID on the startup screen? Previously, non-enterprise personal sign-ins mistakenly showed a Google Cloud Project ID in the startup banner at the top of the terminal. This is now fixed, so personal sign-ins no longer see an ID that has nothing to do with them.

BUGFIX

Complex conversation steps load without crashes and forked histories stay cleanly isolated

Did reopening a conversation with subagent or scheduling steps crash the whole program? Previously, reloading or compacting conversations containing background-task, subagent-management, messaging, or scheduling steps could trigger a stack-overflow crash that halted the program. In addition, when forking a conversation, the new branch mistakenly inherited step output data from steps after the fork point, clashing with freshly generated steps. Both issues are now resolved: loading no longer crashes and forked histories stay cleanly separated.

BUGFIX

Background leaks fixed, canceled requests abort instantly, and CLI quits without delay

Running the CLI all day or canceling workspace creation will no longer leak memory or hold onto orphaned resources in the background. Previously, every conversation session leaked a background poller and timer, steadily accumulating memory over long sessions. If you canceled a conversation or workspace creation, the background continued provisioning resources; aborted requests now halt immediately. Quitting the CLI also used to force an extra 5-second wait for a timeout, but shutdown now severs open streaming connections immediately to exit on the spot. Sluggish memory bloat, stuck background provisioning, and slow exits are all resolved.

Original changelog

Original changelogLong prompts stay intact as context compaction shares budgets across turns

Improved context compaction to spread its user-request budget across all captured prompts, so a long initial instruction is no longer truncated to a small fixed slice when the other prompts in the conversation are short
Improved context compaction to size summary and truncation budgets from the model's full context window instead of the compaction trigger threshold, so compacted summaries and background-task lists are no longer prematurely cut short

Original changelogCustom models support PDFs and stop throwing unsupported mime type errors

Fixed PDF and audio tool outputs and attachments failing with `unsupported mime type` errors on custom models configured in `settings.json`; custom models now accept PDFs by default and honor the `modelFeatures` media flags for images, video, PDF, and audio

Original changelogPressing Ctrl+G to open Vim no longer hangs when editing prompts

Fixed pressing `Ctrl+G` to edit the prompt in a full-screen terminal editor such as `vim` hanging with `Vim: Warning: Output is not to a terminal`; external editors now run against a real terminal stdout

Original changelogVoice dictation no longer erases drafts on timeout and auto-finalizes at 3.5 minutes

Fixed voice dictation sessions longer than 4 minutes failing with a deadline error and erasing the drafted transcription; recordings now automatically stop and finalize at 3 minutes 30 seconds

Original changelogPersonal sign-ins no longer see a Google Cloud Project ID

Fixed the startup banner displaying a Google Cloud Project ID for consumer (non-enterprise) sign-ins

Original changelogComplex conversation steps load without crashes and forked histories stay cleanly isolated

Fixed a stack-overflow crash when loading or compacting conversations containing background-task, subagent-management, messaging, or scheduling steps
Fixed forked conversations inheriting step output data from steps after the fork point, which could collide with new steps produced in the fork

Original changelogBackground leaks fixed, canceled requests abort instantly, and CLI quits without delay

Fixed a background poller and timer leaking for every conversation session, slowly accumulating memory over long-running sessions
Fixed canceled conversation and workspace creation requests continuing to provision resources in the background; aborted requests now stop immediately
Fixed quitting the CLI taking around 5 extra seconds before the process exited; shutdown now cancels open streaming connections immediately instead of waiting for a forced timeout