AiderDesk: äldre versioner att ladda ner

Highlights
📁 File Editor Modal Overhaul: File Tree Sidebar, Tab Context Menus & State Persistence
Navigating and editing project files without leaving your active task just got significantly easier. The workspace file editor modal now features an integrated file tree sidebar, allowing you to browse, expand folders, and open files directly inside the editor view. We have also added tab context menus (Close Others, Close to the Right, Close All) for faster tab hygiene, alongside full editor state persistence - your open tabs, active tab, and unsaved editor content stay intact even if you close and reopen the modal or navigate between views.
⚙️ Dedicated Model Overrides for Compaction & Handoff
You can now configure separate model overrides for conversation compaction and agent handoffs in Context Management settings. High-end reasoning models are ideal for complex coding prompts, but using them for compaction summaries can consume unnecessary tokens and risk hitting rate limits. With this update, you can route background summarization and compaction workloads to faster, cost-effective models (such as Claude 3.5 Haiku, Gemini 2.0 Flash, or GPT-4o-mini) while keeping your primary frontier model focused on code generation. Learn more in the Handoff & Compaction documentation.
🎯 Editable Model Modalities & Capability-Aware Attachment Filtering
Different models excel with different inputs, and the Model Library now makes this explicit and configurable. You can view and edit supported input and output modalities (text, image, audio, video, PDF) for any provider or model. AiderDesk uses these capabilities to automatically filter incompatible file attachments before sending requests to models that cannot process them, preventing frustrating API errors. For custom or unknown model identifiers, attachments are preserved as-is so new endpoints and experimental multimodal workflows continue to work smoothly. Check out the Providers documentation for details.
🤖 Enhanced Task Tools: Prepared Tasks, Execution & Autonomy Controls
Agent task orchestration receives major improvements with expanded controls for Task tools:
- Prepared Tasks: Agents can prepare tasks with initial prompts and start or resume them later without restarting conversations.
- Execution Controls: Support for explicit execution modes (create_only, wait_for_finish, run_in_background).
- Autonomy Settings: Fine-grained autonomy levels (manual, guided, autonomous) can now be passed directly to task executions.
- Readable Tracking: Tool messages in the chat interface now display actual task names rather than raw identifiers, making multi-task workflows much easier to follow.
See the Task Tools documentation for more information.
🔌 Extension Ecosystem: Background Generation, Worktree Hooks & Custom Catalogs
This release introduces substantial capabilities for extension developers:
- Background Context Generation: Extensions can now trigger background text generation and streaming (generateText, streamText) directly within task context.
- Worktree Lifecycle Hooks: New onWorktreeCreated and onWorktreeMerged hooks allow extensions to run project-specific automation, custom environment setups, or branch synchronization scripts when switching working modes.
- Custom Catalogs & Independent Favorites: Extension model selector components can now provide custom model catalogs and maintain their own favorite selections independently from global model settings.
- Reliable Recovery: Fixed a bug where onPromptFinished was missed during agent resume and restart recovery.
Explore the updated Extension API Reference to start building with these new APIs.
Other Changes
- Security & Runtimes:
- Updated Electron, Node.js, and uv runtimes for upstream security vulnerabilities.
- Added automatic Python certificate bundle updates and startup warnings for unpatched Node.js versions.
- Prevented potential OS command injection in extension repository clone paths.
- Provider & Model Configuration: Ad

Highlights
🔄 Automatic Task and Subagent Recovery After Restarts
Agent runs frequently perform multi-step workflows across tools and subagents. In the event of an unexpected application restart or crash, you should never lose completed progress or risk re-executing unsafe actions. AiderDesk now features automatic task and subagent recovery, durably checkpointing streamed assistant responses, tool calls, and finalized outputs as they happen directly into the local application database.
When your project reopens, interrupted runs resume right where they left off. Completed tool calls retain their results instead of repeating, subagents recover under their original identity to avoid duplicate tasks, and unfinished operations are handled according to configurable per-tool recovery modes (Replay safely, Notify interrupted, and Forget unfinished). Non-idempotent actions like shell commands or file edits notify the model to inspect current workspace state before retrying, preventing duplicate side effects. You can fine-tune recovery modes per tool in Settings → Agents → Tools or toggle startup resume in Settings → General → Start Up → Recovery.
📸 Pre-Compaction Context Snapshots Kept for Agents
Context compaction keeps long-running tasks responsive and within model token budgets, but earlier conversation details were previously summarized and replaced. With pre-compaction context snapshots, AiderDesk now saves the entire uncompacted context into sequentially numbered files (context.pre-compaction.001.json) within the task directory before every manual or automatic compaction.
These snapshots are permanently retained and never pruned. Agents running with the built-in system prompt are automatically informed of existing snapshot paths, giving them the ability to inspect earlier messages whenever historical implementation details, past reasoning, or discarded code snippets are needed later in the workflow.
📊 Theme-Aware Mermaid Diagrams with Pele
Visual architecture diagrams and sequence charts are now rendered using the pele library, bringing a substantial visual and usability upgrade to Mermaid rendering in chat. Diagrams adapt to your active theme with coordinated colors, typography, and crisp styling in both light and dark modes.
Diagrams also support smooth streaming updates as your agent writes Mermaid code, keeping the previous valid diagram intact during syntax generation instead of flickering or breaking. Built-in interactive zoom and reset controls make navigating large system architecture diagrams effortless.
🌿 Push Worktree Fixes Directly to Base Branch Upstream
Developing features and bug fixes in git worktrees provides clean isolation, but pushing those fixes back to the main remote previously required extra branch manipulation or switching back to the local repository. The Git push dialog in worktree tasks now includes an option to push directly to the base branch's upstream remote.
With a single checkbox, your worktree commits are pushed straight to the base branch's tracking remote destination, eliminating repetitive Git gymnastics when publishing patches or preparing releases from isolated workspaces.
🛡️ Native Tool Approval for Extension Providers
External agent providers and custom model extensions can now integrate seamlessly with AiderDesk's safety policies via the new ProviderToolApprovalHandler interface. When external agents execute native tools (such as OpenCode native shell or file operations), providers can check tool execution directly against AiderDesk's active approval engine.
This ensures task autonomy settings (Manual, Guided, Autonomous), Power tool approval policies (Always, Ask, Never), bash command deny-lists, and extension approval veto hooks (onToolApproval, onHandleApproval) are fully enforced, giving you uniform governance regardless of whether tools run natively or through AiderDesk.
Other Changes
- UI & Small Screen Responsiveness:
- Fixed dialog overflow on small screens with responsive w