Editor View Articles
Deep dives into the AI-powered Antigravity editor: tab completion, inline editing, Diff View, debugging support, and fixes for common editor troubles.
An Update Notice the Night Before a Deadline: Three Questions I Ask Before Clicking
When an Antigravity update notice appears the night before a deadline, should you update or wait? How I read the changelog, check that I can roll back, and set up a five-minute safety net.
Undo That Rewinds Only the Conversation, and Messaging a Subagent Directly: Three Moments I Hesitated
Antigravity 2.19.1 adds undo for the conversation only, and direct messages to a subagent. Here is what the changelog says, where I draw my own lines, and how to check both safely.
The IDE vanished after Antigravity 2.0: four checks before you try to restore anything
After updating to Antigravity 2.0, the familiar editor, settings, and extensions were gone. Here is why the config folders split in two, how to restore them without overwriting anything, and what to watch for when running the IDE next to 2.0.
The Night Red Squiggles Filled My MCP Config, and What I Checked Before Editing
Red squiggles across your MCP config don't mean the servers are down. Schema validation in the editor answers a different question than the runtime does. Here's the order I now follow, starting with the status rings in /mcp.
How Far to Chase a VS Code Extension That Open VSX Doesn't Carry
Why your settings come across to Antigravity but your extensions don't, how to reconcile the gap with a script, and how to decide between a substitute, a pinned VSIX, moving the job outside the editor, or swapping the registry.
The File Counts Matched. 148 Pairs Disagreed on Code Blocks
My Japanese and English article trees matched at 1,057 files each, yet the bodies had quietly diverged. Here is what counting code blocks and H2 headings across every pair turned up, why a character-length ratio failed to catch any of it, and the 40-line checker I now run before every push.
The Morning My Completions Stopped: Code Was 1.4% of the Repo
When completions stop coming back in Antigravity, restarting the language server often does nothing. Here is how I split the slowness into three layers, counted each one, and asked git whether my ignore patterns were actually matching.
How much of Antigravity's generated commit message I actually keep
Where the Review pane's generated commit message stops being enough, and where I start writing. A prepare-commit-msg hook that adds a Why trailer, plus measured behaviour during rebase, cherry-pick and revert.
When YAML frontmatter rewrites your values without raising an error
Antigravity 2.11.0 renders frontmatter as a formatted card. Chasing the one file that refused to become a card turned up five patterns that parse cleanly but change the value. Here are the measured rules and a 40-line checker.
Charts from Generative UI break the moment you leave the CDN links in
Antigravity 2.11.0 renders HTML artifacts inline, and most of them arrive with CDN references. Here is a 20-line checker that counts external refs, plus the inlining step, with measured numbers.
Building a Verification Loop With Antigravity 2.10.0's Embedded Terminal
Antigravity 2.10.0 puts a terminal in the sidebar. Here is how I pinned my pre-merge checks down to three commands, scoped them to changed files only, and what the measured difference turned out to be.
Three Byte-Level Checks I Run Before an Agent Edits Files That Contain Japanese
When an agent edit swaps a single multi-byte character, git shows it as an ordinary one-line change. Here is how I fold invalid UTF-8, replacement characters, and normalization drift into one pass.
A Triage Order for WebP and Opus Attachments That Never Reach the Agent
Hub 2.9.1 added WebP attachments on August 20, and CLI 1.1.17 fixed Ogg-family audio being rejected by the model on the same day. Here is why rejection happens on the sending side rather than in the file, with the MIME results I actually measured.
I Stopped Eyeballing Agent Diffs, and the 2.8.0 View Limits Are Why
Version 2.8.0 caps how much of a file and how much of a large history diff you can view. Losing the ability to scroll to the end forced a better split: let a script decide what machines can catch, and spend human attention only on what they cannot. Includes a working script and the defects it found in a real repository.
2.6.0 Changed How Hooks Wait. A Triage Order for Turns That Never Finish
When an agent turn never finishes, the cause is often a hook you wrote rather than the model. Here is what changed in IDE 2.6.0, an audit script that finds hooks capable of stalling a turn, and how to give a hook its own cutoff.
The Date Column Was the Most Expensive Part of My Sales CSV — Measuring What Attachments Really Cost
2.4.3 lets you attach .json, .md, and .csv files directly. I rendered the same table eight ways, priced every column in tokens, and boiled it down to a 1,062-token digest. Every number here came from a run on my own machine.
One Space in a Path, and Nine Commands Reported Success While Counting the Wrong Place
A single space in a workspace name sends agent-written commands somewhere else, quietly. Measurements across eleven unquoted-path forms, and the entry-point script that closes the boundary in one cd.
Three Ways to Hand 4,000 Lines of Logs to an Agent — Paste, .txt Attachment, or @ Reference
v2.3.0 added plain-text attachments, which means there are now three ways to hand a long log to an agent — and a new question about which one to pick. Here is how I trim, measure, and decide, with the scripts I actually run.
Your UI Is in Japanese. Your Commit Log Isn't.
Setting your editor's display language does nothing for the language your agents write into the repository. Here is what six weeks of unattended runs actually produced, how to pin output language per audience, and a gate that catches the drift mechanically.
Widening one panel made my agent reviews faster
A field note on turning two quiet additions in Antigravity v2.2.1 — Conversation Width and broader syntax highlighting — into a faster way to read the diffs your agents produce. Small display tweaks, but they changed how quickly I could review.
The Day My Own DSL Stayed Gray: Adding a Minimal TextMate Grammar to Antigravity
When a custom config file you use every day renders as flat gray text, misreads pile up. This walkthrough builds a minimal TextMate grammar and language-configuration so Antigravity highlights your own file type, with working code and the pitfalls that trip people up.
I Only Want to See the Lines the Agent Added: A Changed-Lines Convention Linter
I asked an agent for a small fix, it touched an old file, and the linter threw 13 warnings with no way to tell which were the agent's. Scoping the linter to only the added lines dropped 13 to 3 — about 77% less noise. Here is how to pull added lines out of a diff and check only those, with working code.
Antigravity DevContainer: A Complete Setup Guide for Reproducible AI Development
An end-to-end guide to running Antigravity inside a DevContainer — Docker setup, Ollama integration, secrets, volume persistence, team distribution, and CI parity.
Localizing Antigravity 2.0 to Japanese — The Three-Layer Setup for Menus, Commands, and AI Responses
Installing the Japanese Language Pack in Antigravity 2.0 only translates part of the UI. To get a clean Japanese experience — menus, command palette, AI responses — you need to configure three independent layers. Here is the exact setup I run as an indie developer at Dolice, plus which parts I deliberately leave in English.
When Antigravity Reads Cloud-Synced Files as Empty: The Online-Only Placeholder Trap
A file is right there in Finder, yet the Antigravity agent insists it is empty or missing. The culprit is an online-only placeholder created by cloud sync. Here is how to spot it, hydrate the data, and design a workspace that avoids the problem.
Handing Off IDE Work to the Chat Agent: Passing Context Through a File After the Two-App Split
Since Antigravity 2.0 split into an IDE and a chat-style agent app, context you build up in one does not carry into the other. Here is a file-based approach that makes a single file in your repo the source of truth for handoff, with a schema, a validation script, and a way to pin it with a Guide skill.
Faster Substring Search Changes How You Should Let Agents Explore Code
The 6/26 update made substring search noticeably faster. Rather than treating it as a comfort improvement, here is how to redesign the way agents explore code, budget context, and verify their targets, with measurements from indie development.
The Built-in Guide Skill Is Only Advice — Pair It With a Gate That Mechanically Rejects Antigravity's Output
The v2.2.1 built-in Guide skill raises how often the agent complies, but it is still probabilistic advice. Here is the design for a deterministic gate that reliably stops the violations that slip through, with working code and measured results.
When Antigravity Skips Parts of a Long Attached PDF — and a Gate That Forces It to Cite Sources
How to handle the case where Antigravity answers confidently from a long attached PDF but quietly skips a clause. With working code: a prompt that forces citations, and a gate that verifies each cited quote actually exists in the PDF.
Turning Faster Substring Search into Solid Grounding for Agents in Large Repos
Antigravity's substring search got faster. Rather than stopping at perceived speed, here is how to wire it into a search design that hands agents exactly the right context in a huge codebase, with concrete steps and pitfalls.
The Day My Own Skill Stopped Firing — When the Built-in Guide Skill Collides With Yours
Since the built-in Guide skill arrived, custom skills started getting skipped or double-fired. Here is how to observe which skill is chosen, and how to settle the conflict through descriptions and naming.
What Tripped Me Up First When Antigravity 2.0 Split the IDE and the Agent Into Separate Apps
Antigravity 2.0's modular layout splits the IDE and the chat-style agent into two separate apps. Here is the moment their file states drifted apart on me, and the save discipline I now use to keep a single source of truth.
Splitting a Giant Antigravity Diff Into Meaningful Commits
Are you committing the agent's 400-line diffs as a single blob? Here is a practical workflow, with scripts, for re-splitting an unreviewable bulk commit into one concern per commit.
Precedence for Nested AGENTS.md: A Merge Design for Many Projects in One Workspace
Put several projects in one workspace, each with its own AGENTS.md, and which instruction the agent follows turns ambiguous. Root and per-project rules quietly collide; one wins, or both blend. Taking 'closer is stronger' as the base rule, this designs a merge that distinguishes overriding from appending, with working Python and field notes.
Feeding Spec PDFs to Antigravity 2.1.4: A Practical Attachment Workflow
Field notes on using the PDF attachment added in Antigravity 2.1.4 as a spec-driven implementation workflow: supported formats, the scanned-PDF trap, token cost, and how to verify the output.
Supervising Multiple Agents at Once on the Antigravity 2.0 Desktop: Screen Layout and Interruption Design
How I lay out the screen, score interruption order, and measure my own ceiling on parallel agents in Antigravity 2.0 — with the small scripts and the numbers I actually recorded.
From Gemini CLI to Antigravity CLI: A Working Record of the June 18 Migration
On June 18, Gemini CLI and the Code Assist extension stop serving individual users. Here is my actual record of moving to the Go-based Antigravity CLI: what broke, the command mapping, and the auth and quota traps I hit.
Three Weeks with Antigravity Settings Sync Across Two Macs — A Sync Design for Solo App Development
Notes from three weeks of running Antigravity Settings Sync between a home Mac mini and a portable MacBook Air, written from the perspective of a solo developer working across multiple devices.
Cultivating Antigravity Walkthroughs as a Regression Replay Memo: A Four-Month Operational Log
A four-month log of repurposing Antigravity Walkthroughs from a one-off explainer into a persistent regression replay memo. Includes the naming scheme, the four-section structure, and the concrete numbers behind a roughly 60 percent drop in duplicate bug reports.
VS Code 1.121 and the Agent Host Protocol — Reading the Moment When Editor Boundaries Started Moving Outward
VS Code 1.121 introduced Remote agents and the Agent Host Protocol (AHP), expanded the Claude Agent's Auto mode and BYOK options, and made Markdown Mermaid support standard. Read from an Antigravity user's perspective, this release looks like the moment the editor began stepping outside itself.