All Articles
When a Subagent Never Finishes, Look at the Parent's Unapproved Artifacts First
A subagent that runs all night and never returns is usually not the one that is stuck. Here is how I separate a blocked parent from a blocked child using a short log-scanning script, where the new always proceeds mode helps, and where I stop letting approvals happen automatically.
Deleting Duplicate Rows Will Not Shrink Your Antigravity CLI Conversation Database
A schema-agnostic way to audit conversation database growth, plus measurements showing why deletion reclaims nothing and why freelist_count is the wrong number to trust when you estimate how much you can get back.
Running Antigravity CLI 1.1.13 on a Machine You Cannot Sign In From
I put agy on a box with no browser and the sign-in screen stopped me cold. Here is how direct GEMINI_API_KEY auth from CLI 1.1.13 works, how to confirm it took effect, and why you should not hand it the key your app already uses.
Android 17 Went Canary-Only, So I Gave My Agent the Silence Rules First
Android 17 dropped Developer Previews in favour of rolling Canary builds, which moved the verification deadline onto my side of the table. Here is how I handed the tracking job to an Antigravity agent by designing when it stays quiet, not when it reports.
When Antigravity Holds a Dozen Projects: How I Stopped Hunting for Yesterday's Conversation
As Antigravity projects pile up, the conversation sidebar turns into a morning scrolling ritual. Now that 2.8.0 remembers collapsed state, here is how I reworked project granularity, conversation naming, and launch flags.
How Far to Narrow an Agent's Choices in a 30-Category Wallpaper Classification Pipeline
Asking an agent to pick one of 30 categories per image means re-running every image the moment a definition changes. Here is the reasoning and the implementation behind switching to closed-vocabulary tags plus a deterministic rule mapping.
When a Fast Model Feels Slow, Look at Reasoning Effort Before Switching Models
Antigravity lets you pick a reasoning effort level per model. Here is how I decide between Low, Medium, and High based on the shape of the task, what to check when changing it makes no difference, and a small script for correcting your own judgment with records instead of memory.
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.
Guarding the Turn Boundary in Non-Interactive Runs: A Command Table and a Fail-Closed Gate
A scheduled job meant only to record usage was calling the model on every run. Here is how I split commands into ones that start a turn and ones that do not, built a gate that refuses anything unclassified, and measured it against real scripts.
The Line I Thought Matched Nothing Was Approving Everything: Auditing Empty Allowlist Entries
Allowlist entries that decompose to zero command words matched every command and silently auto-approved it. Here is how I scanned my own config, separated the hole the fix closed from the one it did not, and rewrote matching to a prefix-token comparison.
The Hooks That Get Rejected Are the Cheap Ones: Measuring Matcher Reachability
Hook configurations that can never execute are now rejected at load time. But when I checked my own config against all 21 tool names, the real problems were on the side that passed. A static reachability checker, plus measured numbers on what over-matching actually costs.