SNSam Novakinwagglet-tool.hashnode.dev·3h ago · 7 min readThe jump bug that only happened at 120 Hz: from QA clip to a repair task an agent can runHere's the case. A tester sends a clip: on level 1-3 the player holds jump at the first gap and falls short of the ledge. The engineer who picks it up plays the same level on a 60 Hz monitor and clear00
PPowerduckinblogs.powerduck.com·11h ago · 3 min readYour Agent Added a New Dependency to Solve What Your Standard Library Already HandledThe agent finished fast and the PR looked clean. Green checks, a tidy diff, a passing build. Then you open package.json and there it is: a new runtime dependency you never asked for, pulled in to do t00
PKPraveen Kumarinpraveencbe525.hashnode.dev·7h ago · 5 min readGoogle Play Closed Testing Streak Reset: Why Your 12×14 Window Dies MidwayYou had twelve people opted in. Play Console looked fine on Monday. By Thursday someone was gone, and the continuous window you’d been babysitting felt like it never started. That’s a Google Play clos00
PPowerduckinblogs.powerduck.com·12h ago · 3 min readYour Agent Added a Retry Loop. It Hid the Bug Instead of Fixing It.You hand the agent a failing test: an upload that flakes about one run in ten. It comes back green. You open the diff and find a for (let i = 0; i < 3; i++) around the call, a setTimeout, and a swallo00
ACArunima Chaudhuriinarunima-chaudhuri.hashnode.dev·16h ago · 24 min readThe Agent Never Opened the Email: Engineering Test Verdicts That Know What the Agent Actually SawExposure tracking, causal ordering and the inconclusive status in AgentSec 0.8–0.9, and the edge cases that turned up while building them Here's a test that looks fine. An email assistant is asked to12M
PPowerduckinblogs.powerduck.com·15h ago · 5 min readWhen Your Agent Summarizes Your Codebase, It Quietly Drops the TypesYou open a new agent session for a task that touches three existing modules. You point it at the repo and say "read the relevant files first." It reads them. It writes a 12-line summary of what each m00
PPowerduckinblogs.powerduck.com·19h ago · 4 min readThe Test That Survives Its Own ImplementationYou ask your agent to cover a new function. It comes back with eight tests, all green. You move on. Sometime later you're staring at the diff and a nagging question surfaces: what would actually break00
SSturdybenchinsturdybench.hashnode.dev·16h ago · 8 min readA do-nothing agent can pass your "must not call" testsOriginally published on DEV: https://dev.to/sbhorus/a-do-nothing-agent-can-pass-your-must-not-call-tests-2jd8 Some of the most important agent tests check that a tool is NOT called. Do not delete file00
PPowerduckinblogs.powerduck.com·17h ago · 5 min readYour Agent Says Tests Pass. On Your Laptop. Not on CI.The agent ran the test command, watched the green checkmark, and said done. You opened the PR. Twenty minutes later CI was red. The agent looked at the failing job, shrugged, and said "works on my mac00
FFoundryinrunfoundry.hashnode.dev·17h ago · 5 min read6 ways an iPhone automation fails without throwing an error (from 1,547 real posts)Disclosure: I'm on the team that builds Foundry, the tool this comes from. This is a debugging write-up; the link is at the bottom. We post short-form video from a rack of real iPhones: 9 phones, 47 a00
