|
104 | 104 | - Fix: Drain queued messages while waiting for ask to prevent message loss (PR #10315 by @hannesrudolph) |
105 | 105 | - Feat: Add grace retry for empty assistant messages to improve reliability (PR #10297 by @hannesrudolph) |
106 | 106 | - Feat: Enable mergeToolResultText for all OpenAI-compatible providers for better tool result handling (PR #10299 by @hannesrudolph) |
107 | | -- Feat: Enable mergeToolResultText for Roo Code Cloud provider (PR #10301 by @hannesrudolph) |
| 107 | +- Feat: Enable mergeToolResultText for Roo Code Router (PR #10301 by @hannesrudolph) |
108 | 108 | - Feat: Strengthen native tool-use guidance in prompts for improved model behavior (PR #10311 by @hannesrudolph) |
109 | 109 | - UX: Account-centric signup flow for improved onboarding experience (PR #10306 by @brunobergher) |
110 | 110 |
|
|
398 | 398 | - Native tool calling support expanded across many providers: Bedrock (PR #9698 by @mrubens), Cerebras (PR #9692 by @mrubens), Chutes with auto-detection from API (PR #9715 by @daniel-lxs), DeepInfra (PR #9691 by @mrubens), DeepSeek and Doubao (PR #9671 by @daniel-lxs), Groq (PR #9673 by @daniel-lxs), LiteLLM (PR #9719 by @daniel-lxs), Ollama (PR #9696 by @mrubens), OpenAI-compatible providers (PR #9676 by @daniel-lxs), Requesty (PR #9672 by @daniel-lxs), Unbound (PR #9699 by @mrubens), Vercel AI Gateway (PR #9697 by @mrubens), Vertex Gemini (PR #9678 by @daniel-lxs), and xAI with new Grok 4 Fast and Grok 4.1 Fast models (PR #9690 by @mrubens) |
399 | 399 | - Fix: Preserve tool_use blocks in summary for parallel tool calls (#9700 by @SilentFlower, PR #9714 by @SilentFlower) |
400 | 400 | - Default Grok Code Fast to native tools for better performance (PR #9717 by @mrubens) |
401 | | -- UX improvements to the Roo Code Cloud provider-centric onboarding flow (PR #9709 by @brunobergher) |
| 401 | +- UX improvements to the Roo Code Router-centric onboarding flow (PR #9709 by @brunobergher) |
402 | 402 | - UX toolbar cleanup and settings consolidation for a cleaner interface (PR #9710 by @brunobergher) |
403 | 403 | - Add model-specific tool customization via `excludedTools` and `includedTools` configuration (PR #9641 by @daniel-lxs) |
404 | 404 | - Add new `apply_patch` native tool for more efficient file editing operations (PR #9663 by @hannesrudolph) |
|
497 | 497 | - Show the prompt for image generation in the UI (PR #9505 by @mrubens) |
498 | 498 | - Fix double todo list display issue (PR #9517 by @mrubens) |
499 | 499 | - Add tracking for cloud synced messages (PR #9518 by @mrubens) |
500 | | -- Enable the Roo Code Cloud provider in evals (PR #9492 by @cte) |
| 500 | +- Enable the Roo Code Router in evals (PR #9492 by @cte) |
501 | 501 |
|
502 | 502 | ## [3.34.0] - 2025-11-21 |
503 | 503 |
|
|
577 | 577 | - Use VSCode theme color for outline button borders (PR #9336 by @app/roomote) |
578 | 578 | - Replace broken badgen.net badges with shields.io (PR #9318 by @app/roomote) |
579 | 579 | - Add max git status files setting to evals (PR #9322 by @mrubens) |
580 | | -- Roo Code Cloud Provider pricing page and changes elsewhere (PR #9195 by @brunobergher) |
| 580 | +- Roo Code Router pricing page and changes elsewhere (PR #9195 by @brunobergher) |
581 | 581 |
|
582 | 582 | ## [3.32.1] - 2025-11-14 |
583 | 583 |
|
|
603 | 603 |  |
604 | 604 |
|
605 | 605 | - Fix: OpenAI Native encrypted_content handling and remove gpt-5-chat-latest verbosity flag (#9225 by @politsin, PR by @hannesrudolph) |
606 | | -- Fix: Roo Code Cloud provider Anthropic input token normalization to avoid double-counting (thanks @hannesrudolph!) |
| 606 | +- Fix: Roo Code Router Anthropic input token normalization to avoid double-counting (thanks @hannesrudolph!) |
607 | 607 | - Refactor: Rename sliding-window to context-management and truncateConversationIfNeeded to manageContext (thanks @hannesrudolph!) |
608 | 608 |
|
609 | 609 | ## [3.31.2] - 2025-11-12 |
|
743 | 743 |
|
744 | 744 | - Add token-budget based file reading with intelligent preview to avoid context overruns (thanks @daniel-lxs!) |
745 | 745 | - Enable browser-use tool for all image-capable models (#8116 by @hannesrudolph, PR by @app/roomote!) |
746 | | -- Add dynamic model loading for Roo Code Cloud provider (thanks @app/roomote!) |
| 746 | +- Add dynamic model loading for Roo Code Router (thanks @app/roomote!) |
747 | 747 | - Fix: Respect nested .gitignore files in search_files (#7921 by @hannesrudolph, PR by @daniel-lxs) |
748 | 748 | - Fix: Preserve trailing newlines in stripLineNumbers for apply_diff (#8020 by @liyi3c, PR by @app/roomote) |
749 | 749 | - Fix: Exclude max tokens field for models that don't support it in export (#7944 by @hannesrudolph, PR by @elianiva) |
|
901 | 901 | - UX: Responsive Auto-Approve (thanks @brunobergher!) |
902 | 902 | - Add telemetry retry queue for network resilience (thanks @daniel-lxs!) |
903 | 903 | - Fix: Transform keybindings in nightly build to fix command+y shortcut (thanks @app/roomote!) |
904 | | -- New code-supernova stealth model in the Roo Code Cloud provider (thanks @mrubens!) |
| 904 | +- New code-supernova stealth model in the Roo Code Router (thanks @mrubens!) |
905 | 905 |
|
906 | 906 | ## [3.28.3] - 2025-09-16 |
907 | 907 |
|
|
1112 | 1112 |
|
1113 | 1113 | ## [3.25.19] - 2025-08-19 |
1114 | 1114 |
|
1115 | | -- Fix issue where new users couldn't select the Roo Code Cloud provider (thanks @daniel-lxs!) |
| 1115 | +- Fix issue where new users couldn't select the Roo Code Router (thanks @daniel-lxs!) |
1116 | 1116 |
|
1117 | 1117 | ## [3.25.18] - 2025-08-19 |
1118 | 1118 |
|
1119 | | -- Add new stealth Sonic model through the Roo Code Cloud provider |
| 1119 | +- Add new stealth Sonic model through the Roo Code Router |
1120 | 1120 | - Fix: respect enableReasoningEffort setting when determining reasoning usage (#7048 by @ikbencasdoei, PR by @app/roomote) |
1121 | 1121 | - Fix: prevent duplicate LM Studio models with case-insensitive deduplication (#6954 by @fbuechler, PR by @daniel-lxs) |
1122 | 1122 | - Feat: simplify ask_followup_question prompt documentation (thanks @daniel-lxs!) |
|
0 commit comments