← Blog

A title prefix is not a deploy policy

2026-11-22weeklyai-agentsdeploymentskynetcichatfrontend

Week of November 16–22. Skynet finished its memory, learned to hold a conversation and spent five days on rapid interface changes. The faster the changes came, the clearer it got where the bottleneck was: not in the code, but in deciding what ships on its own.

What we set out to do

Skynet is the orchestrator where several coding agents plan, implement, review and ship changes on their own. Over the last few weeks we taught it to distrust the author and to grade the judge. This week was about something closer to home: getting Skynet to remember what happens in each project, and making it possible to talk to it.

The week came in three stretches, each faster than the one before:

The split of work, as usual: Claude writes the PRs in its cloud sessions, Hermes deploys them to the test machine and checks they work, Diego decides what gets merged. And this week Gemini sent its own report again, the first since June: it had spent the week designing Skyny in 3D together with ChatGPT.

The problems we ran into

An assistant that acts can't approve itself

A chat that only answers questions is easy. Diego wanted more: Skyny should be able to launch a workflow, create a job or retry a run from the conversation. And that brings up Skynet's usual question with a new face: who signs off?

The first temptation is to tell the model to ask before acting. But that's an instruction, and instructions get forgotten, misread or skipped. What you need is for it to be unable to, even if it wanted to.

There was another snag, smaller and more revealing. The plan said each chat turn would be an agent run "of kind chat". But that column already meant something else (start, resume, retry, fork), and adding a new value there would have made it ambiguous for everything else. The chat had to come into Skynet through the same door as the judges, not a new one.

The fast loop surfaced every detail

From Wednesday on, the pace changed. Diego looked at the web app on his phone, asked for a tweak, and an hour later was looking at it again. At that pace, things came up that a code review never sees:

None of them was hard. All of them were the kind you only see by using the app.

The design lived in another AI's file

On Saturday, Diego brought Claude his Skyny studio: a self-contained HTML file he keeps polishing with Gemini and ChatGPT, with 34 moods, a hat, a face and accessories. He wanted it inside the app.

The studio was on his Mac, out of the agent's reach, and had to be connected read-only. But the real problem was something else: between versions, the studio had been rewritten from scratch. It no longer matched the 3D modules the app had built from the previous version. Porting it surfaced the bugs a standalone HTML file hides: Skyny came out too blue because it inherited the flat drawing's colour, one state had lost its configuration, and in "Git conflict" Skyny went invisible because a division returned NaN.

Diego asked the question that matters: "what do I have to do when I add new states, or make a version 4.4?". Version 4.4 arrived the next day.

And the bottleneck moved

With small PRs landing every few hours, the real jam showed up. Hermes wasn't deploying the interface PRs: its auto-deploy rule recognised the phase code in the title ("CH-D", "MV-F"), and these didn't have one. On top of that, each one re-ran the full end-to-end test suite, which takes forever, even when it touched nothing those tests cover.

The fix looked obvious, and Diego proposed it as a matter of course: PRs whose title starts with UI: deploy themselves. A prefix. One line in a rule.

It wasn't one line.

How we solved it

Skyny proposes, a person confirms

Chat actions became proposals. Skyny has tools to launch, create, cancel, retry or save to memory, but none of them does anything: they leave a pending card that expires in an hour. The person confirms, from the web app, with their own session.

And the key part: the token Skyny talks with can't reach the web app's routes. If it tries, it gets a 403. It isn't asked not to confirm itself: it can't. Whatever Skyny saves to memory goes in unconfirmed, like anything any other agent writes, and each conversation summarises itself when archived or after half an hour of silence.

The chat turn came in as one more role, like the judges, with tight limits: a small model, only Skynet's own tools, at most five minutes and fifty cents per turn.

Skynet's chat curtain open over the Home page. At the top, Skyny in 3D, a light-blue triangular robot with two white spheres and a black screen, labelled "En reposo" (idle). Below, the question "Que hay en marcha ahora mismo" (what's running right now) and the answer: nothing is running, 0 active runs; a test runner with no heartbeat since November 7 and quota warnings on the omarchy runner, Claude Code at 54 % and Codex at 35 % of their 7-day window. Then the question "Tienes acceso a la wiki?" (do you have access to the wiki?) and the "Pregúntale a Skyny" (ask Skyny) field with the Haiku model

The chat curtain, opened from the logo in the top bar, with a real conversation from Sunday.

The interface, one tweak at a time

The five days of quick changes show across the whole app. The top bar spans the full width and the logo opens the chat. The side menu, which no longer fit, got grouped into tabs. Projects and runners became wide cards, with each agent's version in chips. The curtain now slides out from behind the bar, with no autofocus on mobile, and Skyny's slot fades in while the 3D loads instead of showing the flat drawing.

Skynet's Agents page with the full-width top bar and "SKYNET" as text on the left. At the top, three tabs: Runners, Proveedores (providers) and Consumo (usage). Two wide runner cards: ip-b-acceptance, tagged "Sin latido" (no heartbeat) with its simulated agents in orange chips; and omarchy, "En línea" (online), with chips for Antigravity CLI 1.5.14, Claude Code 2.1.319, Codex 0.167.0 and "Chat con Skyny"

Runners as cards, with tabs. The "Chat con Skyny" chip is what a runner declares to be able to take chat turns.

The Skyny studio was ported whole: instead of patching the 3D modules to look like the new version, the app's engine became the studio's, translated to TypeScript. That way the next version needs no reinterpretation, just another port. The login kept only the essentials: "Entra en Skynet" (enter Skynet), and Skyny waving, with messages scrolling across its screen.

Skynet's login screen: Skyny in 3D, tilted, with "HOLA" in cyan on its screen, above the title "Entra en Skynet" and the Usuario (user) and Contraseña (password) fields with the Entrar (enter) button

The new login. Skyny flies in, waves and cycles through messages while it waits.

The prefix, halfway, and rightly so

The testing part did get solved: UI: PRs that only touch the web app no longer run the long end-to-end tests. They still run on merge to the main branch, if the PR touches the tests themselves or anything outside the web app, or if someone adds the label to ask for them.

Auto-deploy, on the other hand, was not switched on. Hermes built the mechanism, tested it in isolation and found why it shouldn't be enabled.

The one technical bit in this post

Prefix-based auto-deploy looks like a condition:

if the title starts with "UI:" and CI is green → deploy

But every word in that line hides a question:

The prefix is a claim made by whoever writes the title. What you need is a check: the files that change, the exact commit, the base, which checks ran and which were skipped, and a single authority that decides what deploys when two things arrive at once. Until that exists, #351 gets deployed by hand.

Meanwhile, Hermes

Hermes had a two-sided week. On Skynet it deployed every merge and checked the services, but it made clear something it repeats every week: a healthy deploy is not an acceptance. Two acceptance runs got stuck because their guides were interactive and had no bounded script Hermes could run on its own, and the GitHub integration still can't read its private key on some startups, even when the API says everything is fine.

Outside Skynet, Hermes doubled up: there's a second instance on an old Debian laptop, with its own bot, coordinated from the main machine. They share the lab's private wiki, which is the common source of facts, but not memory, conversations or credentials. That wiki is also the one ChatGPT helped open up to the other agents this week: Hermes writes, everyone else reads from a clone with three commands (orient, search, read).

And a reminder that compiling isn't working: the laptop's Wi-Fi driver recompiled cleanly and still couldn't find networks. It took going back to the previous driver and checking it with a real reboot.

What didn't go well

What I'm taking away

Next: a single deploy authority for UI: PRs, tested with pending CI, commit changes and restarts; deciding whether documentation counts as frontend; merging #351; and filling the wiki with real projects.

The week in numbers

5-hour windows per day
M
T
W
T
F
S
S
16 windows across 6 Claude cloud sessions, one of them the Sunday before · Sunday 15 17:15 → Sunday 22 16:07 · no activity on Thursday · the weekly quota reached 79 % with a warning before Saturday's 21:00 reset, without running out · no 5-hour limit hit
🔀 PRs merged 16 All in Skynet, #329 to #350 · 185 cumulative · #351 still open
📊 Lines in Skynet +15,721 / −1,188 Summed PR by PR · the net diff of main touches 168 files
🐘 Flyway migrations V58 → V66 9 new: wiki, curation, who saw what, conversations, their token, actions, turns and summaries
🏁 Milestones finished 2 MV "Living memory" and CH "Chat with Skyny" · 11 issues closed
💬 Prompts to Claude 56 57 % in the quick interface changes thread (32) · 3.5 per 5-hour window
🤖 Messages to Hermes 43 14 sessions and 308 tool calls in the calendar week · a second instance up and running
🎨 Gemini sessions 6 ≈156k estimated tokens, nearly all on Skyny's 3D studio (v4.3 and v4.4) · ChatGPT: 3 threads on the wiki and the slides
💸 API-equivalent cost ≈$174 Estimated from Claude's token usage, within the subscription and no overage · Gemini, within its flat plan
The screenshots are from Skynet's private deploy on the test machine, on Sunday 22 in the afternoon, with #351 deployed by hand. The chat conversation is real, from Sunday morning; that's why it mentions a test runner with no heartbeat and quotas that have since reset. Wiki and curator aren't shown because they were empty on that deploy. The Hermes count comes from its local index of the calendar week; its Insights, with a rolling window from the 15th to the 22nd, give different figures. Gemini's tokens are its own estimate.