--- title: "Five Releases in One Day: The Engine Is Foxl Code Itself" description: "How Foxl shipped five production releases in a single day using Foxl Code on its own monorepo: a same-day critical hotfix with a live regression test, a native iOS glass experiment reverted on real-device evidence, and the persistent project memory that makes the pace ordinary." author: "Foxl Team" date_published: "2026-07-22" date_modified: "2026-07-22" canonical_url: "https://foxl.ai/blog/five-releases-one-day" markdown_url: "https://foxl.ai/blog/five-releases-one-day/index.md" image: "https://foxl.ai/blog/five-releases-one-day-cover.png" social_image: "https://foxl.ai/blog/social/five-releases-one-day.png" content_type: "Deep dive" topics: ["Agentic coding","Release engineering","Dogfooding"] products: ["Foxl Code","Foxl Agent"] --- # Five Releases in One Day: The Engine Is Foxl Code Itself > On July 22 Foxl shipped v0.4.15 through v0.4.19 - five production releases, each hitting six web surfaces, a notarized macOS build, and iOS TestFlight. This is the story of the loop that made that pace ordinary: Foxl Code working on the Foxl monorepo, with a human supplying taste and one-line bug reports, including a critical incident fixed the hour it was reported and an experiment shipped, disproven on hardware, and reverted the same day. - Author: Foxl Team - Published: 2026-07-22 - Last reviewed: 2026-07-22 - Reading time: 6 minutes - Canonical HTML: [https://foxl.ai/blog/five-releases-one-day]() ![The five Foxl releases of July 22, 2026 - v0.4.15 through v0.4.19 - each shipped to web, macOS, and iOS by Foxl Code.]() On July 22, 2026, Foxl shipped five production releases in one day: v0.4.15 through v0.4.19. Each one went everywhere - six web surfaces, a signed and notarized macOS build, and an iOS TestFlight build. This post is not about heroics or an all-nighter. It is about the engine that made the pace ordinary, because the engine is the product: Foxl builds Foxl. ## What actually shipped The day was not five patch bumps. It was a full arc of real product work, including one production incident found and fixed within the hour: - **v0.4.15** restored the Skills, Channels, and custom MCP tabs that a Settings refactor had orphaned, and fixed a family of mobile cold-start bugs that were all one iOS lifecycle fact in disguise. - **v0.4.16** was a critical hotfix: a relay-internal field was leaking upstream and every model returned an empty reply on mobile whenever the desktop was offline. Diagnosed against a local relay, root-fixed, regression-tested against the real provider, and released - same day it was reported. - **v0.4.17** made errors impossible to miss (every failed turn now answers back with an in-conversation explanation), fixed Stop on mobile, and opened GPT-5.6 Luna to the free tier. - **v0.4.18** reworked the mobile header, turned the phone terminal into a full-screen page, and shipped an experiment: real native Liquid Glass on iOS via a new Capacitor plugin. - **v0.4.19** reverted that experiment - it failed on real devices, for a reason worth understanding - and finished the terminal work with a reconnect control and a duplicate-tab race fix. ## The loop that makes five releases normal Every one of those releases followed the same loop, and the loop is Foxl Code driving the Foxl monorepo. A person describes what they want - often as tersely as a screenshot and one sentence of annoyance. The agent reads the code, finds the root cause, writes the fix, runs the typecheckers and both build variants, deploys the staging or production surface it can safely deploy, and writes the changelog entry in the same commit. The person stays in the loop the whole time, but as an editor and a taste function, not as the typist. The releases themselves are one command each. A release script bumps nine package manifests together, deploys the relay, the orchestrator, three web apps, the docs, and the marketing site, builds and notarizes the desktop app, and uploads it through a release bot. A second script builds and uploads the iOS app. The agent runs both, watches them, and handles the aftermath - committing the version bumps, moving the git tag to the right commit, verifying every surface responds, and checking that no source maps leaked into the binary. When the release script died halfway through v0.4.17 because of a stray environment variable, the agent finished the remaining surfaces by hand, in order, and then wrote the failure into its own operating notes so the next release would not repeat it. ## Speed is a memory problem, not a typing problem The un-glamorous secret of the pace is accumulated context. The agent keeps a persistent memory of the project: which install flags break the monorepo, which release script leaves the tag on the wrong commit, which test suite once exhausted the machine's ports and must never auto-spawn its server. Five releases in a day is what it looks like when none of that knowledge has to be rediscovered - the second release of the day inherits everything the first one learned, and release five runs cleaner than release one. The same memory is why bug reports written in one line still land as root-cause fixes. "Stop does nothing on my phone" became a two-layer diagnosis - an abort signal dropped by a fetch interceptor, plus iOS swallowing the tap during keyboard dismissal - because the agent already knew the app's tunnel architecture cold and could trace the signal path instead of guessing. ## Shipping a mistake and unshipping it, same day The most honest part of the day is the experiment that failed. v0.4.18 shipped real native Liquid Glass on iOS - actual system glass views tracked behind the web content, built as a new Capacitor plugin in a few hours by porting the architecture of a macOS Electron library. It compiled, it ran in the simulator, and on a real device it was wrong: black bands at the top and bottom, and no glass at all. The reason was architectural, not a bug. The macOS trick works because a Mac window can be transparent - glass behind the web content samples the desktop *behind the window*. An iPhone app is fullscreen; behind its web view there is only the app's own black container, so the glass had nothing to sample, and making the web view transparent just exposed the black. v0.4.19 reverted it the same day, kept the plugin repository as a reference, and recorded the analysis in the project's memory so the idea does not get re-attempted in the same shape. Fast iteration is not just shipping fast - it is un-shipping fast, with the lesson written down. ## What the human does all day Reading this you might picture automation running unattended. It is the opposite: the day was a continuous conversation. The human sent screenshots of a cramped terminal UI and said "this is terrible, make it slide in from the right." They caught the header peeking above the terminal and said cover it. They tested glass on a real device and said revert it. Every release carried their taste; none of them carried their typing. That division - human judgment, agent execution, shared memory - is the whole product thesis, and July 22 is what it looks like on a good day. ## The numbers - 5 releases: v0.4.15, v0.4.16, v0.4.17, v0.4.18, v0.4.19 - Each release: 6 web surfaces deployed, a notarized macOS build, an iOS TestFlight build (builds 1426 through 1453) - 1 production incident root-fixed with a live regression test, same day it was reported - 1 experiment shipped, disproven on hardware, and reverted - 1 new open-ended capability for free users (GPT-5.6 Luna), 1 new plugin repository, 2 blog posts - including this one, which Foxl Code also wrote If you want the same loop on your own repository, that is what Foxl Code is: describe the change, review the diff, keep the taste, skip the typing. ## References and further reading 1. [Foxl changelog]() - Release 2. [Foxl Code]() - Reference 3. [Download Foxl]() - Reference