The Eclipse Theia Community Release 2026-05

We are happy to announce the fourteenth Eclipse Theia community release, “2026-05,” incorporating the latest advances from Theia releases 1.69, 1.70, and 1.71.

New to Eclipse Theia? It is the next-generation platform for building IDEs and tools for the web or desktop, based on modern web technologies. With Theia AI, you can build AI-powered tools and IDEs with ease. Visit the Theia website for more info.

The Theia project also delivers a product: the Theia IDE, a modern, AI-powered, and open IDE for cloud and desktop environments. The Theia IDE is based on Theia and includes advanced AI-powered features. See the Theia IDE website or download the latest release for a hands-on experience!

Community releases are provided quarterly and serve as stable anchors for downstream adopters. Each combines features, fixes, and hardening from monthly releases. Learn more about the advantages of the community release, or visit Theia’s releases page.

During this release cycle, Eclipse Theia was strongly represented at Open Community Experience 2026 (OCX26), the Eclipse Foundation’s flagship event held in Brussels, with three dedicated talks covering the platform from different angles. Eclipse Theia — News from the next-gen tools platform by Thomas Mäder (Castle Ridge Software) and Jonas Helming (EclipseSource) provides a broad update on the Theia platform, Theia AI, and the Theia IDE. AI in Action: The ultimate live demo with Theia AI by Jonas Helming is a slide-free, fully live demonstration of AI-native development with Theia AI. And Eclipse Theia in practice: Getting started and lessons from the field by Stefan Dirix takes a practical, experience-driven look at building custom tools on Theia.

In related ecosystem news, the Eclipse Foundation Newsletter recently published an overview article on Eclipse Theia: The Eclipse Foundation tool platform in production, and the Samsung Sokatoa adopter story takes a closer look at how Samsung leveraged Theia to build a highly specialised, domain-specific tool for GPU profiling and debugging on Android.

Now let’s explore the key highlights from this fourteenth Theia community release!

Highlights of the Theia 2026-05 Community Release

This community release ships cumulative improvements from releases 1.69, 1.70, and 1.71, totalling 242 merged pull requests. For a comprehensive list of changes, please see the individual announcements. Here are some top highlights:

AI Coding Features in the Theia IDE Graduate from Beta

The headline news of this community release: with Theia 1.70, AI Coding features in the Theia IDE officially graduate from beta. This includes the IDE-specific AI Views, the Theia Coder agent, and the related agents. The underlying framework, Theia AI, already left beta about a year ago, and the AI Coding features built on top have been in active production use ever since. Reflecting this milestone, the default workbench layout now opens the AI Chat and Terminal panels by default for new workspaces, making AI features a first-class, always-visible part of the IDE.

Of course, leaving beta does not mean the features are “complete” — AI tooling continues to evolve at remarkable speed, and the next community release will already bring further refinements. The video below shows a complete AI-driven development workflow in the Theia IDE with Theia Coder, including plan mode, E2E testing, shell access, GitHub integration, and the new capability concept.

Workspace Trust for AI Features

Theia 1.71 closes an important gap by gating all AI features behind Workspace Trust. Until a folder is trusted, the IDE runs in Restricted Mode: chat input, inline completion, and AI commands are disabled, workspace-scoped prompt templates and AI preferences are ignored, and external images embedded in AI chat markdown are blocked. The AI views and menus stay visible so users can discover them, but a clear “Manage Workspace Trust” prompt is shown until trust is granted. This complements the broader Workspace Trust framework that protects tasks, debug sessions, extensions, and MCP servers. A new dedicated Workspace Trust documentation page covers the trust dialog, status bar indicator, and security.workspace.trust.* settings.

Agent Capabilities: A New Way to Compose AI Agents

The AI agent ecosystem has grown rapidly — MCP servers, Skills, sub-agents, prompt fragments, tool functions — and with that growth comes complexity. Theia 1.69 introduces Capabilities, a new concept that consolidates all of these building blocks under a single, user-friendly umbrella. Rather than asking users to understand and configure each technical mechanism individually, an agent advertises what it can do, and users toggle those options on or off without worrying about the plumbing underneath.

For the Theia Coder agent this looks like compact toggle chips for Shell Execution, GitHub, and AppTester directly in the chat input — flip them on for the current request, and Coder gains those skills.

For advanced users, a generic Capabilities Panel (Ctrl+Shift+.) exposes the full searchable tree of all available Skills, MCP server functions, built-in tool functions, prompt fragments, and agent delegation targets. For adopters building on Theia AI, Capabilities are backed by a simple {{capability:fragment-id [default on|off]}} syntax in prompt templates — agent builders can encapsulate rich behavior (tools, delegation, contextual prompts) behind a single named toggle without having to manage UI plumbing.

Theia Coder and Architect: Streamlined Defaults

Across 1.69 and 1.70, the Coder and Architect agents have been significantly streamlined. The previously experimental “next” prompt has been promoted to the standard Agent Mode for Coder, the Architect’s plan mode is now the default experience for the Architect, and the older legacy variants have been retired to reduce confusion. The AppTester agent now defaults to the Chrome DevTools-based autonomous testing approach. Coder also received access to launch configuration tools, enabling it to start, manage, and stop long-running applications (e.g. a dev server) when implementing and testing features.

Building on this, Theia 1.70 makes Agent Mode the default for Coder for all new users, delivering the full agentic coding experience out of the box. The very first time a request is made, a clear confirmation dialog explains that Agent Mode can write to workspace files, letting users choose to continue or switch to Edit Mode (and persist that as the new default).

For adopters, the confirmation logic is cleanly exposed via a dedicated AgentModeConfirmationService interface, making it straightforward to customize or skip the flow.

PR Review Agent

Theia 1.71 introduces a new @pr-reviewer agent that conducts structured pull request reviews by orchestrating the GitHub agent, workspace tools, and agent delegation. As part of this, a generic UserInteractionTool is introduced that allows any agent to ask the user structured questions with labelled option buttons, an optional free-text fallback, and navigable links to open files and diffs in the workspace. A dedicated blog post walks through the agent in detail, and the demo below shows it in action.

Smarter Shell Command Permissions

The shell command confirmation experience receives two major upgrades. Theia 1.69 introduces a smart pattern-based permission UI: instead of generic Allow/Deny buttons, the confirmation dialog now offers split buttons with suggestions like “Always allow git *” or “Always allow git commit *”, ordered from broadest to most specific, plus a “Deny with reason…” action that lets the user give direct feedback to the agent. The underlying analyzer parses compound commands and correctly handles quoted strings, pipes, and redirects, so suggestions are derived from the actual sub-commands rather than the raw text.

Theia 1.71 complements this with command descriptions in the confirmation dialog: the LLM can now provide an optional description for each proposed shell command, helping users make more informed approve/deny decisions.

GitHub Copilot Integration Matures

The GitHub Copilot integration introduced in the previous community release matures significantly across 1.69, 1.70, and 1.71. Highlights include a confirmation dialog before sign-out (1.69), automatic model discovery and OAuth App migration in 1.70 (models are now fetched dynamically from the Copilot API and re-discovered automatically when authentication state or the enterprise URL changes), a new ai-features.copilot.enterpriseUrl preference fully wired up for both API and discovery, and a customizable OAuth configuration in 1.71 so downstream adopters can plug in their own GitHub OAuth app and authentication dialog messages.

Provider-Agnostic Reasoning Level Selector

Theia 1.69 introduced configurable thinking mode per provider, per model, or per agent — including a one-off toggle in the chat input. Theia 1.71 takes the next step and replaces the legacy binary thinking flag plus budget-tokens field with a provider-agnostic reasoning level selector. The new ReasoningSettings abstraction supports levels from off through minimal, low, medium, high, to auto. Each LLM provider declares a ReasoningSupport capability on its model description, and a compact UI selector appears next to the chat mode selector — visible only for reasoning-capable models. Both effort-based APIs (Anthropic adaptive thinking, OpenAI, Gemini 3) and budget-based APIs (Anthropic legacy, Gemini 2.5) are supported.

Token Usage Indicator and Warnings

Theia 1.71 adds a per-session token usage indicator to the chat view: a compact circular progress ring next to the send button fills proportionally with usage, turning yellow at 90% and red at 100%+, and the chat input border tints accordingly. A hover tooltip provides a breakdown of input, output, cached, and total tokens. Complementing this, a configurable warning notification alerts users when a session’s total token usage crosses a threshold, offering quick actions to compact the session or start a new chat. Both features can be tuned via ai-features.chat.tokenUsageIndicator and ai-features.chat.tokenUsageWarning.

Major SCM Improvements

The Source Control experience receives a substantial overhaul over the three releases. Theia 1.70 introduces multi-root SCM support with a new SCM Repositories Widget: when a workspace contains multiple git repositories — including worktrees or nested repos — all repositories are listed in a dedicated panel within the SCM view container, grouped by provider ID, and the badge count aggregates changes across all repositories.

Theia 1.70 also adds Git blame annotations directly in the editor and the status bar, so you can immediately see who last changed the current line or file without leaving the current context.

Theia 1.71 then adds the long-requested Source Control History Graph — a fully rendered commit DAG that lives inside the SCM view container. The new view enables extensions like the built-in Git extension to render a commit history with branch lane lines, ref badges, author information, tooltips, and context menus. The implementation includes a VS Code-compatible plugin API for SourceControlHistoryProvider, a paginated graph model, and a pure function for DAG lane computation supporting linear, merge, branch-out, octopus, and sibling topologies. Ref badges are deduplicated (local and remote refs collapse), and lane colors make it easy to follow branches visually.

Finally, the long-deprecated @theia/git extension has been fully removed — Git support is now entirely provided by the VS Code built-in Git extension.

Dev Container Improvements

Theia 1.71 delivers a comprehensive set of Dev Container improvements. SSH credential injection and Git identity sharing automatically forward keys, host .gitconfig, and SSH agent into the container. Auto-reopen in last active dev container reconnects on application restart. A new “Reopen in Container” suggestion notification appears when opening a workspace that contains a devcontainer.json. A Rebuild Container command removes the old container and creates a fresh one while preserving the devcontainer file context. And a new “Attach to Running Container” command lets you connect to any already-running Docker container — even those without a devcontainer.json. Beyond these user-facing features, the release also fixes variable resolution for embedded strings in devcontainer.json, ensures all mount options are passed through correctly, and fixes JSON quoting when injecting preferences.

Terminal Command History via Shell Integration

Theia 1.70 introduces terminal command history via shell integration. The terminal now tracks individual commands along with their output, making it easy to review what happened in a session. This works out of the box with bash and zsh, as well as with task terminals across all platforms. Users can enable command history via the experimental terminal.integrated.enableCommandHistory preference, and visual command block dividers via terminal.integrated.enableCommandSeparator. Most importantly, this is a foundational improvement enabling smarter AI terminal interactions: AI agents can now precisely retrieve the output of specific commands.

ANSI Color Support in the Output View

The Output view in Theia 1.71 now parses and renders ANSI SGR escape sequences, replacing the previous raw escape code display with properly styled inline decorations. Colors, bold, italic, and underline styles render correctly via Monaco editor decorations across both light and dark themes — build tools, test runners, and language servers that emit ANSI-colored output now look as intended.

Test Extension Support Improvements

Theia 1.71 fixes several long-standing issues that prevented VS Code test extensions like Python unittest and Playwright Test from working reliably, including workspace folder reference equality in workspace.getWorkspaceFolder(), root-level test discovery, test state flushing in TestRun.end(), and identity preservation in TestItemCollection.replace(). On the UX side, the Test Output panel now opens automatically when a test run starts, and a new “Show Test Output” toolbar button has been added to the Test Runs view.

Base Technology Updates

Across the three releases, Theia keeps its foundation current with the broader ecosystem. The Monaco editor has been uplifted to version 1.108, bringing improved inline completions and various rendering and accessibility enhancements. Node.js 24 is now supported (Node.js 20 dropped), Electron has been updated to 39.8.7 in 1.71 — fixing an intermittent Windows splash-screen crash — and VS Code API compatibility has been bumped to 1.116.0 (from 1.110.1 in 1.70 and 1.109.4 in 1.69). VS Code built-in extensions are kept aligned accordingly.

Additional Highlights

This community release includes many more improvements beyond the headlines: hands-on MCP server CRUD management in the AI Configuration view, MCP Roots support, persistent capability settings, improved fuzzy search prioritizing substring matches across Quick Open, settings, keybindings, and file explorer, a configurable search.exclude preference, an auto-save-when-no-errors mode, a window zoom status bar item with secondary-window synchronization, a comprehensive breakpoint identity refactoring with proper multi-session support, fully functional Extension Host debugging in Electron, a refreshed chat welcome screen with resumable session cards, smarter completion notifications, inline image rendering in chat requests, keyboard accessibility improvements throughout the AI Chat view, AI proxy support for all providers, RPC promise rejection guarantees, expanded start-up performance logging, autosave on window focus loss, hover tooltips that allow clicking and text selection, the new #productName AI variable for white-labeling, and updated default AI models across providers — including Claude Opus 4.7, the GPT-5.5 family, and the latest Gemini 3.x previews.

For a comprehensive breakdown, please read the in-depth release news:

• Eclipse Theia 1.69 announcement
• Eclipse Theia 1.70 announcement
• Eclipse Theia 1.71 announcement

Build or Extend Your Own IDE or Tool with Eclipse Theia

If you are interested in building custom tools or IDEs based on Eclipse Theia, EclipseSource provides consulting and implementation services for Eclipse Theia, for AI-powered tools and IDEs, for Tools or extensions based on VS Code as well as for web-based tools in general. We also provide a Eclipse Theia online training that you can take anytime for a running start with Theia extension development. If you want to extend Theia with features or bug fixes, EclipseSource provides sponsored development for Theia, too. Finally, for cloud deployments we offer consulting and support for web-based tools.

👉 Contact us to find the perfect (AI-driven) solution for your projects!

👉 Subscribe to our YouTube channel.