With scheduled agents, I now look for runs that never happened before I look for failures
My run ledger showed a 100% success rate while the evening slot had not fired for two weeks. Here is the reconciliation I now run against an expected-fire table, with measured notes on cron expansion, exit codes, and how the ledger itself gets written.
A Custom Tool That Says any_of Loses Its Constraint Without Ever Erroring
I tested ten spelling variants in custom tool parameter definitions to see which ones fail loudly and which slip through unnoticed, then measured how argument validation shifts once normalization lands.
Pointing GOOGLE_GEMINI_BASE_URL at Your Own Gateway Does Not Change Who Holds the Key
I pointed the Antigravity CLI at a gateway of my own and recorded exactly which credentials travelled with it. Authorization is dropped across a cross-origin redirect, but the API key header survives every hop. Here is the measurement, and how I moved the key off my laptop.
Snapshot Your Agents' Effective Scope So You Notice the Day a Default Changes
Antigravity 1.1.25 made Markdown-defined custom agents inherit the surrounding skills, rules, and subagents by default. Here is the snapshot-and-diff routine I now use to check whether an agent I meant to keep narrow quietly got wider after an update.
The Five Days Between the iOS 27 RC and Release — I Check Init Order and Entitlement Restore Before Layout
A record of how I narrow the agent's search scope during the short window before an OS release — by launch path rather than by screen. Includes the audit script I run to catch consent and ads init ordering, entitlement restore gaps, and hardcoded size branches.
A dependency without musllinux wheels doesn't fail on Alpine. It just gets slower
On Alpine, a dependency without musllinux wheels can quietly fall back to pure Python. Protobuf went from 0.043ms to 36.2ms, and pip reported no error.
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.
Why Filename Search Misses Every Error String in Your Repo
Antigravity 2.12 improved partial filename search. Measuring name lookups against full-text search across a 2,088-file repository, the reading cost differed by 67x and error strings hit filenames only 4.5% of the time. Here is where the line actually falls.
The work-root guard I run before letting an agent near several repositories
When several repositories share one machine, an agent's working root is remarkably easy to mix up. Here is a small guard that compares resolved paths, tested against seven inputs.
Why I took the show-or-not decision away from every dialog
A paywall prompt, a review request and a rewarded-ad confirmation landed on the same frame. Here is how I moved the show-or-not decision out of each dialog into a single gate, how I rewrote the agent instructions as invariants, and how a CI check keeps it that way.
Before You Narrow the Page Range in Antigravity 2.11.0, Find Your Resolution Floor
I measured the new page range and MediaResolution options in view_file against a 240-page document. Resolution moved the numbers more than the page range did, and setting it too low drops words without raising a single error.
What @ Includes Actually Shrink When You Split Agent Rule Files
I split my rule files using Antigravity 2.11.0's @path/to/file includes and measured the before and after across four real repositories. Maintenance surface dropped 62 percent. What a session actually reads dropped 1.7 percent. Here is why, plus the code that catches the silent failure mode.