docs(jetbrains): rewrite plugin marketplace description

The plugin.xml description advertised inline autocomplete and browser
automation, neither of which the JetBrains plugin ships, and undersold
the actual differentiators (remote-dev-native split-mode architecture,
Agent Manager's per-task git worktrees, run/debug without new windows,
GitHub-native PR/diff visibility). Replace it with an accurate,
feature-complete listing covering all six pillars, sourced from the
plugin's feature/pitch doc.
This commit is contained in:
kirillk
2026-08-31 14:39:53 -04:00
parent a29fc822e8
commit 2736ab68c1
@@ -3,10 +3,83 @@
<vendor url="https://kilo.ai">Kilo Code</vendor>
<description><![CDATA[
Open Source AI coding agent that generates code from natural language, automates tasks,
and runs terminal commands. Features inline autocomplete, browser automation, automated
refactoring, and custom modes for planning, coding, and debugging.
Supports 500+ AI models including Claude (Anthropic), Gemini, Grok, GPT, Codex and GLM.
<p>
<b>Kilo Code</b> is an open-source AI coding agent for JetBrains IDEs, built for both local
and remote development. Run multiple agents on different tasks at the same time — each in its
own isolated git worktree — without opening a new IDE window per task. The entire UI is native
Swing (no embedded browser, no Node.js), so it works identically locally and in JetBrains
Remote Development split mode over SSH, VMs, or Dev Containers.
</p>
<p><b>Built for remote development</b></p>
<ul>
<li>No JCEF embedded browser anywhere in the UI — renders the same locally and through JetBrains Gateway.</li>
<li>True split-mode architecture: the frontend runs on your machine, the agent server runs on the host next to your code.</li>
<li>No Node.js dependency — a native <code>kilo</code> binary is downloaded per OS and architecture.</li>
<li>Dev Container aware: if a project is opened so the backend can't see container files, Kilo tells you to reopen via Gateway instead of failing silently.</li>
<li>Resilient to flaky connections — long-running calls survive backend restarts and reconnects.</li>
</ul>
<p><b>Agent Manager — many tasks, one IDE frame</b></p>
<ul>
<li>Every task gets its own git worktree: own branch, own working directory, own uncommitted changes.</li>
<li>Start from a new worktree off a base branch, an existing branch, or directly from a GitHub PR URL.</li>
<li><em>Continue in Worktree</em> — fork an in-progress session's uncommitted changes into a fresh isolated worktree mid-conversation.</li>
<li>One panel showing every task in flight with live PR status, diff stats, and run state.</li>
<li>Optional per-worktree setup scripts (POSIX / PowerShell / CMD) that run automatically in their own terminal tab.</li>
</ul>
<p><b>Run and debug without juggling windows</b></p>
<ul>
<li>Your existing Run Configurations (Gradle, external system, program-based) are transplanted onto each worktree with the correct working directory.</li>
<li>Live run indicators per worktree, plus Build and Rebuild from the same popup.</li>
<li>Need real breakpoint debugging? <em>Open in New Frame</em> opens one worktree as its own project window — reusing an open frame when there is one, and working correctly in remote sessions too.</li>
</ul>
<p><b>GitHub-native workflow</b></p>
<ul>
<li>PR number, title, and state in the session header, clickable through to the browser.</li>
<li>Diff versus the PR base branch with file and line counts, plus a full diff viewer.</li>
<li>Uncommitted local changes tracked separately from the base diff.</li>
<li>Import any existing PR into an isolated worktree to review, continue, or debug it.</li>
<li>Guided setup when <code>git</code> or the GitHub CLI is missing or unauthenticated, instead of a silent failure.</li>
</ul>
<p><b>600+ models, your keys or ours</b></p>
<ul>
<li>Claude, Gemini, GPT, Grok, GLM, and hundreds more from every major provider, switchable without leaving the IDE.</li>
<li>Bring your own API keys or use Kilo credits.</li>
<li>Pin a specific model to a specific custom agent so it never drifts between sessions.</li>
<li>A separate fast, cheap model tier for high-frequency operations like subagent orchestration.</li>
<li>Data-sensitivity badges flag models that may train on your prompts.</li>
<li>Enterprise model access controls: org admins can block models or providers account-wide by training policy, retention policy, or datacenter location.</li>
</ul>
<p><b>Powered by Kilo CLI</b></p>
<ul>
<li>The same open-source agent runtime behind the Kilo CLI, VS Code extension, and Kilo Cloud.</li>
<li>One shared <code>kilo.jsonc</code> config — set up agents, providers, and preferences once and use them on every surface.</li>
<li>Built-in tools, MCP servers, semantic search, and LSP integration come from the shared runtime.</li>
<li>One agent server per IDE instance serving your main workspace and every open worktree.</li>
</ul>
<p><b>Also included</b></p>
<ul>
<li>Custom agents and modes with full create, edit, import, and export support.</li>
<li>MCP server management with live connection status.</li>
<li>Custom slash-command workflows backed by editable Markdown files.</li>
<li>Skills management, including custom local and remote skill sources.</li>
<li>Session checkpoints — revert to any prior message and redo forward, with per-file diff stats.</li>
<li>Granular auto-approve permissions with per-tool Allow / Ask / Deny rules and queued approval requests.</li>
<li>Session sharing via a public link.</li>
<li>Smart context management: auto-compaction, stale tool-output pruning, and ignore patterns for large repos.</li>
<li>Automatic settings, MCP config, and state migration from the older Roo/Kilo JetBrains plugin.</li>
</ul>
<p>
<a href="https://kilo.ai">kilo.ai</a> &middot;
<a href="https://github.com/Kilo-Org/kilocode">Source on GitHub</a>
</p>
]]></description>
<content>