|
1 | 1 | # Roo Code Changelog |
2 | 2 |
|
3 | | -## [3.27.0] - 2025-09-05 |
4 | | - |
5 | | - |
6 | | - |
7 | | -- Add: User message editing and deletion functionality (thanks @NaccOll!) |
8 | | -- Add: Kimi K2-0905 model support in Chutes provider (#7700 by @pwilkin, PR by @app/roomote) |
9 | | -- Fix: Prevent stack overflow in codebase indexing for large projects (#7588 by @StarTrai1, PR by @daniel-lxs) |
10 | | -- Fix: Resolve race condition in Gemini Grounding Sources by improving code design (#6372 by @daniel-lxs, PR by @HahaBill) |
11 | | -- Fix: Preserve conversation context by retrying with full conversation on invalid previous_response_id (thanks @daniel-lxs!) |
12 | | -- Fix: Identify MCP and slash command config path in multiple folder workspaces (#6720 by @kfuglsang, PR by @NaccOll) |
13 | | -- Fix: Handle array paths from VSCode terminal profiles correctly (#7695 by @Amosvcc, PR by @app/roomote) |
14 | | -- Fix: Improve WelcomeView styling and readability (thanks @daniel-lxs!) |
15 | | -- Fix: Resolve CI e2e test ETIMEDOUT errors when downloading VS Code (thanks @daniel-lxs!) |
16 | | - |
17 | | -## [3.26.7] - 2025-09-04 |
18 | | - |
19 | | - |
20 | | - |
21 | | -- Feature: Add OpenAI Responses API service tiers (flex/priority) with UI selector and pricing (thanks @hannesrudolph!) |
22 | | -- Feature: Add DeepInfra as a model provider in Roo Code (#7661 by @Thachnh, PR by @Thachnh) |
23 | | -- Feature: Update kimi-k2-0905-preview and kimi-k2-turbo-preview models on the Moonshot provider (thanks @CellenLee!) |
24 | | -- Feature: Add kimi-k2-0905-preview to Groq, Moonshot, and Fireworks (thanks @daniel-lxs and Cline!) |
25 | | -- Fix: Prevent countdown timer from showing in history for answered follow-up questions (#7624 by @XuyiK, PR by @daniel-lxs) |
26 | | -- Fix: Moonshot's maximum return token count limited to 1024 issue resolved (#6936 by @greyishsong, PR by @wangxiaolong100) |
27 | | -- Fix: Add error transform to cryptic OpenAI SDK errors when API key is invalid (#7483 by @A0nameless0man, PR by @app/roomote) |
28 | | -- Fix: Validate MCP tool exists before execution (#7631 by @R-omk, PR by @app/roomote) |
29 | | -- Fix: Handle zsh glob qualifiers correctly (thanks @mrubens!) |
30 | | -- Fix: Handle zsh process substitution correctly (thanks @mrubens!) |
31 | | -- Fix: Minor zh-TW Traditional Chinese locale typo fix (thanks @PeterDaveHello!) |
32 | | - |
33 | | -## [3.26.6] - 2025-09-03 |
34 | | - |
35 | | - |
36 | | - |
37 | | -- Add experimental run_slash_command tool to let the model initiate slash commands (thanks @app/roomote!) |
38 | | -- Fix: use askApproval wrapper in insert_content and search_and_replace tools (#7648 by @hannesrudolph, PR by @app/roomote) |
39 | | -- Add Kimi K2 Turbo model configuration to moonshotModels (thanks @wangxiaolong100!) |
40 | | -- Fix: preserve scroll position when switching tabs in settings (thanks @DC-Dancao!) |
41 | | - |
42 | | -## [3.26.5] - 2025-09-03 |
43 | | - |
44 | | - |
45 | | - |
46 | | -- feat: Add support for Qwen3 235B A22B Thinking 2507 model in chutes (thanks @mohammad154!) |
47 | | -- feat: Add auto-approve support for MCP access_resource tool (#7565 by @m-ibm, PR by @daniel-lxs) |
48 | | -- feat: Add configurable embedding batch size for code indexing (#7356 by @BenLampson, PR by @app/roomote) |
49 | | -- fix: Add cache reporting support for OpenAI-Native provider (thanks @hannesrudolph!) |
50 | | -- feat: Move message queue to the extension host for better performance (thanks @cte!) |
51 | | - |
52 | | -## [3.26.4] - 2025-09-01 |
53 | | - |
54 | | - |
55 | | - |
56 | | -- Optimize memory usage for image handling in webview (thanks @daniel-lxs!) |
57 | | -- Fix: Special tokens should not break task processing (#7539 by @pwilkin, PR by @pwilkin) |
58 | | -- Add Ollama API key support for Turbo mode (#7147 by @LivioGama, PR by @app/roomote) |
59 | | -- Rename Account tab to Cloud tab for clarity (thanks @app/roomote!) |
60 | | -- Add kangaroo-themed release image generation (thanks @mrubens!) |
61 | | - |
62 | | -## [3.26.3] - 2025-08-29 |
63 | | - |
64 | | - |
65 | | - |
66 | | -- Add optional input image parameter to image generation tool (thanks @roomote!) |
67 | | -- Refactor: Flatten image generation settings structure (thanks @daniel-lxs!) |
68 | | -- Show console logging in vitests when the --no-silent flag is set (thanks @hassoncs!) |
69 | | - |
70 | 3 | ## [3.26.2] - 2025-08-28 |
71 | 4 |
|
72 | | - |
73 | | - |
74 | 5 | - feat: Add experimental image generation tool with OpenRouter integration (thanks @daniel-lxs!) |
75 | 6 | - Fix: Resolve GPT-5 Responses API issues with condensing and image support (#7334 by @nlbuescher, PR by @daniel-lxs) |
76 | 7 | - Fix: Hide .rooignore'd files from environment details by default (#7368 by @AlexBlack772, PR by @app/roomote) |
77 | 8 | - Fix: Exclude browser scroll actions from repetition detection (#7470 by @cgrierson-smartsheet, PR by @app/roomote) |
78 | 9 |
|
79 | 10 | ## [3.26.1] - 2025-08-27 |
80 | 11 |
|
81 | | - |
82 | | - |
83 | 12 | - Add Vercel AI Gateway provider integration (thanks @joshualipman123!) |
84 | 13 | - Add support for Vercel embeddings (thanks @mrubens!) |
85 | 14 | - Enable on-disk storage for Qdrant vectors and HNSW index (thanks @daniel-lxs!) |
|
90 | 19 |
|
91 | 20 | ## [3.26.0] - 2025-08-26 |
92 | 21 |
|
93 | | - |
94 | | - |
95 | 22 | - Sonic -> Grok Code Fast |
96 | 23 | - feat: Add Qwen Code CLI API Support with OAuth Authentication (thanks @evinelias and Cline!) |
97 | 24 | - feat: Add Deepseek v3.1 to Fireworks AI provider (#7374 by @dmarkey, PR by @app/roomote) |
|
0 commit comments