Release v3.36.5

[3.36.5] - 2025-12-11

• Add: GPT-5.2 model to openai-native provider (PR #10024 by @hannesrudolph)
• Add: Toggle for Enter key behavior in chat input allowing users to configure whether Enter sends or creates new line (#8555 by @lmtr0, PR #10002 by @hannesrudolph)
• Add: App version to telemetry exception captures and filter 402 errors (PR #9996 by @daniel-lxs)
• Fix: Handle empty Gemini responses and reasoning loops to prevent infinite retries (PR #10007 by @hannesrudolph)
• Fix: Add missing tool_result blocks to prevent API errors when tool results are expected (PR #10015 by @daniel-lxs)
• Fix: Filter orphaned tool_results when more results than tool_uses to prevent message validation errors (PR #10027 by @daniel-lxs)
• Fix: Add general API endpoints for Z.ai provider (#9879 by @richtong, PR #9894 by @roomote)
• Fix: Apply versioned settings on nightly builds (PR #9997 by @hannesrudolph)
• Remove: Glama provider (PR #9801 by @hannesrudolph)
• Remove: Deprecated list_code_definition_names tool (PR #10005 by @hannesrudolph)

Release v3.36.4

[3.36.4] - 2025-12-10

• Add error details modal with on-demand display for improved error visibility when debugging issues (PR #9985 by @roomote)
• Fix: Prevent premature rawChunkTracker clearing for MCP tools, improving reliability of MCP tool streaming (PR #9993 by @daniel-lxs)
• Fix: Filter out 429 rate limit errors from API error telemetry for cleaner metrics (PR #9987 by @daniel-lxs)
• Fix: Correct TODO list display order in chat view to show items in proper sequence (PR #9991 by @roomote)

Release v3.36.3

[3.36.3] - 2025-12-09

• Adds support for minimal and medium reasoning effort levels in the Gemini provider implementation (PR #9973 by @hannesrudolph)
• Unified context-management architecture with improved UX for better conversation context handling (PR #9795 by @hannesrudolph)
• Update DeepSeek models to V3.2 with new pricing (PR #9962 by @hannesrudolph)
• Add versioned settings support with minPluginVersion gating for Roo provider (PR #9934 by @hannesrudolph)
• Make Architect mode save plans to /plans directory and gitignore it (PR #9944 by @brunobergher)
• Add streaming tool stats and token usage throttling for improved performance (PR #9926 by @hannesrudolph)
• Add search_replace native tool for single-replacement operations (PR #9918 by @hannesrudolph)
• Add timeout configuration to OpenAI Compatible Provider Client (PR #9898 by @dcbartlett)
• Add xhigh reasoning effort option for gpt-5.1-codex-max (PR #9900 by @andrewginns)
• Add tool preferences configuration for xAI models (PR #9923 by @hannesrudolph)
• Add ability to save screenshots from the browser tool (PR #9963 by @mrubens)
• Add DeepSeek V3-2 support for Baseten Provider (PR #9861 by @AlexKer)
• Add Kimi, MiniMax, and Qwen model configurations for Bedrock (PR #9905 by @app/roomote)
• Add announcement support CTA and social icons (PR #9945 by @hannesrudolph)
• Default to using native tools when supported on OpenRouter (PR #9878 by @mrubens)
• Update xAI models catalog with latest models (PR #9872 by @hannesrudolph)
• Tweaks to Baseten model definitions (PR #9866 by @mrubens)
• Stop making count_tokens requests to improve performance (PR #9884 by @mrubens)
• Refactor: Decouple tools from system prompt for better modularity (PR #9784 by @daniel-lxs)
• Refactor: Consolidate ThinkingBudget components and fix disable handling (PR #9930 by @hannesrudolph)
• Add API error telemetry to OpenRouter provider (PR #9953 by @daniel-lxs)
• Evals UI: Make eval runs deleteable (PR #9909 by @mrubens)
• Web: Product pages (PR #9865 by @brunobergher)
• Fix: Respect explicit supportsReasoningEffort array values (PR #9970 by @hannesrudolph)
• Fix: Validate and fix tool_result IDs before API requests (PR #9952 by @daniel-lxs)
• Fix: Always show tool protocol selector for openai-compatible provider (PR #9966 by @hannesrudolph)
• Fix: Return undefined instead of 0 for disabled API timeout (PR #9960 by @hannesrudolph)
• Fix: Display actual API error message instead of generic text on retry (PR #9954 by @hannesrudolph)
• Fix: Add finish_reason processing to xai.ts provider (PR #9929 by @daniel-lxs)
• Fix: Exclude apply_diff from native tools when diffEnabled is false (PR #9920 by @app/roomote)
• Fix: Suppress 'ask promise was ignored' error in handleError (PR #9914 by @daniel-lxs)
• Fix: Process finish_reason to emit tool_call_end events (PR #9927 by @daniel-lxs)
• Fix: Use foreground color for context-management icons (PR #9912 by @hannesrudolph)
• Fix: Sanitize removed/invalid API providers to prevent infinite loop (PR #9869 by @hannesrudolph)
• Improve OpenAI error messages to be more useful (PR #9639 by @mrubens)
• Improve cloud job error logging for RCC provider errors (PR #9924 by @cte)
• Improve error logs for parseToolCall exceptions (PR #9857 by @cte)

Release v3.36.2

[3.36.2] - 2025-12-04

• Restrict GPT-5 tool set to apply_patch for improved compatibility (PR #9853 by @hannesrudolph)
• Add dynamic settings support for Roo models from API, allowing model-specific configurations to be fetched dynamically (PR #9852 by @hannesrudolph)
• Fix: Resolve Chutes provider model fetching issue (PR #9854 by @cte)

Release v3.36.1

[3.36.1] - 2025-12-04

• Add MessageManager layer for centralized history coordination, fixing message synchronization issues (PR #9842 by @hannesrudolph)
• Fix: Prevent cascading truncation loop by only truncating visible messages (PR #9844 by @hannesrudolph)
• Fix: Handle unknown/invalid native tool calls to prevent extension freeze (PR #9834 by @daniel-lxs)
• Always enable reasoning for models that require it (PR #9836 by @cte)
• ChatView: Smoother stick-to-bottom behavior during streaming (PR #8999 by @hannesrudolph)
• UX: Improved error messages and documentation links (PR #9777 by @brunobergher)
• Fix: Overly round follow-up question suggestions styling (PR #9829 by @brunobergher)
• Add symlink support for slash commands in .roo/commands folder (PR #9838 by @mrubens)
• Ignore input to the execa terminal process for safer command execution (PR #9827 by @mrubens)
• Be safer about large file reads (PR #9843 by @jr)
• Add gpt-5.1-codex-max model to OpenAI provider (PR #9848 by @hannesrudolph)
• Evals UI: Add filtering, bulk delete, tool consolidation, and run notes (PR #9837 by @hannesrudolph)
• Evals UI: Add multi-model launch and UI improvements (PR #9845 by @hannesrudolph)
• Web: New pricing page (PR #9821 by @brunobergher)

Release v3.36.0

[3.36.0] - 2025-12-04

• Fix: Restore context when rewinding after condense (#8295 by @hannesrudolph, PR #9665 by @hannesrudolph)
• Add reasoning_details support to Roo provider for enhanced model reasoning visibility (PR #9796 by @app/roomote)
• Default to native tools for all models in the Roo provider for improved performance (PR #9811 by @mrubens)
• Enable search_and_replace for Minimax models (PR #9780 by @mrubens)
• Fix: Resolve Vercel AI Gateway model fetching issues (PR #9791 by @cte)
• Fix: Apply conservative max tokens for Cerebras provider (PR #9804 by @sebastiand-cerebras)
• Fix: Remove omission detection logic to eliminate false positives (#9785 by @Michaelzag, PR #9787 by @app/roomote)
• Refactor: Remove deprecated insert_content tool (PR #9751 by @daniel-lxs)
• Chore: Hide parallel tool calls experiment and disable feature (PR #9798 by @hannesrudolph)
• Update next.js documentation site dependencies (PR #9799 by @jr)
• Fix: Correct download count display on homepage (PR #9807 by @mrubens)

Release v3.35.5

[3.35.5] - 2025-12-03

• Feat: Add provider routing selection for OpenRouter embeddings (#9144 by @SannidhyaSah, PR #9693 by @SannidhyaSah)
• Default Minimax M2 to native tool calling (PR #9778 by @mrubens)
• Sanitize the native tool calls to fix a bug with Gemini (PR #9769 by @mrubens)
• UX: Updates to CloudView (PR #9776 by @roomote)

Release v3.35.4

[3.35.4] - 2025-12-02

• Fix: Handle malformed native tool calls to prevent hanging (PR #9758 by @daniel-lxs)
• Fix: Remove reasoning toggles for GLM-4.5 and GLM-4.6 on z.ai provider (PR #9752 by @roomote)
• Refactor: Remove line_count parameter from write_to_file tool (PR #9667 by @hannesrudolph)

Release v3.35.3

[3.35.3] - 2025-12-02

• Switch to new welcome view for improved onboarding experience (PR #9741 by @mrubens)
• Update homepage with latest changes (PR #9675 by @brunobergher)
• Improve privacy for stealth models by adding vendor confidentiality section to system prompt (PR #9742 by @mrubens)

Release v3.35.2

[3.35.2] - 2025-12-01

• Allow models to contain default temperature settings for provider-specific optimal defaults (PR #9734 by @mrubens)
• Add tag-based native tool calling detection for Roo provider models (PR #9735 by @mrubens)
• Enable native tool support for all LiteLLM models by default (PR #9736 by @mrubens)
• Pass app version to provider for improved request tracking (PR #9730 by @cte)