v0.126.0

Added

• Added configuration options to allow for persisting the SQLite database.
• Add Mermaid diagram support to AI chat markdown rendering.
• Render <details>/<summary> HTML in AI chat markdown.
• Allow AI chat MCP servers to act as the logged-in Backstage user via the new useBackstageUserToken option, so user-context tools like auth.who-am-i work without a static external-access token.

Changed

• Strip reasoning content from past AI chat assistant messages to reclaim context tokens for Claude conversations.
• Replace the fa-kubernetes Font Awesome icon with an inline SVG and remove the Font Awesome kit integration.
• Replace @terasky/backstage-plugin-catalog-mcp-backend with the built-in catalog.query-catalog-entities action from @backstage/plugin-mcp-actions-backend.

Fixed

• Fix AI chat input freezing after typing dead keys (e.g., backtick on German keyboard).

Removed

• Remove the custom getCurrentUserInfo AI chat agent tool, superseded by the upstream auth.who-am-i tool from the mcp-actions MCP server.

See ./docs/releases/v0.126.0-changelog.md for more information.

v0.125.0

Added

• Persist AI chat conversations and add a conversation history page with rename, delete, batch delete, and pagination, plus a history view in the chat drawer.
• Add a getDate tool to the AI chat agent for retrieving the current date and time.
• Prune older tool outputs in AI chat once cumulative tool I/O exceeds a configurable budget (aiChat.pruning.reservedTokens, aiChat.pruning.minimumSavingsTokens).

Changed

• Report AI chat context size, output tokens, and cost by requesting token usage from OpenAI-compatible streaming responses (vLLM/KServe).
• Clarify tool use in the muster system prompt to avoid calling internal tools via muster's call_tool.

Fixed

• Re-observe the element when the ref target changes in useContainerDimensions.
• Reject empty titles in PATCH /conversations/:id/title with HTTP 400.

See ./docs/releases/v0.125.0-changelog.md for more information.

v0.124.4

Added

• Make sidebar logo image height configurable via app.branding.logo.height.

Fixed

• Avoid flashing the default logo while the branding manifest is loading.

See ./docs/releases/v0.124.4-changelog.md for more information.

v0.124.3

Added

• Allow overriding the AI chat context window size via aiChat.contextWindow in app-config.

Changed

• Improve markdown table rendering in AI chat: tables are now horizontally scrollable with better cell spacing.

Fixed

• Cache-bust custom branding logo URLs so replaced logos appear immediately instead of being served stale from the browser cache.

See ./docs/releases/v0.124.3-changelog.md for more information.

v0.124.2

Changed

• Decouple custom branding from the gs-backend plugin so branding assets are served by a dedicated backend plugin and work without gs: config.

See ./docs/releases/v0.124.2-changelog.md for more information.

v0.124.1

Fixed

• Fix helm chart to allow for branding configmap.

See ./docs/releases/v0.124.1-changelog.md for more information.

v0.124.0

Added

• Add custom branding asset support with logo overrides, allowing UI logo customization via mounted volumes without code changes.

See ./docs/releases/v0.124.0-changelog.md for more information.

v0.123.0

Added

• Add BackendTrafficPolicy template to the helm chart, to be able to customize HTTP connection settings.

Changed

• Redesign tool call and tool group UI in AI chat with compact inline layout, argument summary previews, and inline status icons.

Fixed

• Fix deprecation warning for the user settings General page by migrating to the new configSchema option.
• Fix missing key prop warning on the scaffolder sidebar item.
• Flush SSE chunks through compression middleware so streamed AI responses reach the client in real time.

See ./docs/releases/v0.123.0-changelog.md for more information.

v0.122.3

Changed

• Stream reasoning tokens live in the AI chat and redesign the Reasoning block: auto-opens while the model is reasoning, "Thinking Xs…" / "Thought for Ys" trigger, char-by-char text reveal with auto-scroll, borderless quote-style visual aligned with modern chat UIs.

See ./docs/releases/v0.122.3-changelog.md for more information.

v0.122.2

Changed

• Stream reasoning tokens from OpenAI-compatible models (vLLM) to the AI chat UI by switching the aiChat.openai.api: chat path to @ai-sdk/openai-compatible and unconditionally rendering the Reasoning/ReasoningGroup slots in Thread.tsx.

See ./docs/releases/v0.122.2-changelog.md for more information.