DeepSeek Harness keeps saying Everything is a Plugin, meaning features are all built as plugins. Version 0.2.1 moved one step further and started managing where plugins come from: rc.1 added an entry that lets users discover and install plugins from custom plugin index sources.
Anyone writing an AI chat client runs into this: the model does not hand you the answer in one go. It dribbles out token by token, wedging tool calls, code blocks and stretches of thinking in between. The user staring at the screen is really watching a tree grow while someone keeps rearranging it.
The most common way to make an agent drive software right now is to let it look at screenshots, find buttons, and click coordinates. It works, but it is brittle. Resize a window, move a button a notch, let a page load half a beat slow, and it starts clicking blindly.
Completion is guesswork, go-to-definition is luck, and you do not dare press rename. On October 15, JetBrains turned the Java and Kotlin engine from IntelliJ IDEA into a language server extension and shipped 1.0, installable in VS Code, Cursor, and Google Antigravity.
Number one. You paste a chunk of logs into your agent client to chase down a problem, and the logs carry a line DEEPSEEK_API_KEY=sk-.... Problem solved, and that line is still sitting in the session history.
You have an agent write some Kotlin. It says it’s done. Now what?
A general-purpose agent writing ArkTS will crash and burn, for exactly three reasons. It does not know ArkTS decorators or build commands; it has no official docs to look things up in, so it invents APIs from memory; and even when the code is right, it has no idea how to build the package, install it on a device, and ship it to the app store.
A bit over a month ago, Claude Code refused to support AGENTS.md — the industry convention already adopted by plenty of projects and coding agents — and Shopify CEO Tobi Lütke publicly warned he was ready to drop it. Anthropic’s reasoning at the time sounded reasonable: different models need different context and instructions.
Adding AI to Flutter used to mean two roads: stuff the model key into the app and call it directly, or hand-assemble requests with http. The first is handing over the keys; the second has you hand-crafting a shoddy framework by day three, patching in retries, streaming, tool calls and structured output one at a time.
On-device search used to be assembly work. Images had to go through a captioning model to become text, audio had to be transcribed, video had to be frame-extracted and subtitled, and then all of it got thrown at a text embedding model. Every modality you added meant another chain, another slice of latency, another pile of intermediates.
An engineer was doing size optimization on his own iOS build and found that one extra compiler flag shrank the bundle by 15 MiB. He filed an issue with a reproduction on a public project and data from real devices, and opened a pull request that same night.
By the time a cross-platform project reaches release, there is usually more than one distribution path. One through Google Play, one straight from your own site, and sometimes a test build for the QA folks. Android’s developer verification reprices the entry cost of each path, and the three bills are not calculated the same way at all.