|
1 | 1 | # kilo-code |
2 | 2 |
|
| 3 | +## 4.140.0 |
| 4 | + |
| 5 | +### Minor Changes |
| 6 | + |
| 7 | +- [#4538](https://github.com/Kilo-Org/kilocode/pull/4538) [`459b95c`](https://github.com/Kilo-Org/kilocode/commit/459b95cbf78de10fce597e3467120e52020d1114) Thanks [@chrarnoldus](https://github.com/chrarnoldus)! - Added gemini-3-flash-preview model |
| 8 | + |
| 9 | +### Patch Changes |
| 10 | + |
| 11 | +- [#4530](https://github.com/Kilo-Org/kilocode/pull/4530) [`782347e`](https://github.com/Kilo-Org/kilocode/commit/782347e9ed6cbaf42c88285cb8576801cd178d96) Thanks [@alvinward](https://github.com/alvinward)! - Add GLM-4.6V model support for z.ai provider |
| 12 | + |
| 13 | +- [#4509](https://github.com/Kilo-Org/kilocode/pull/4509) [`8a9fddd`](https://github.com/Kilo-Org/kilocode/commit/8a9fddd8311633c3085516ab6255bb027aff81d6) Thanks [@kevinvandijk](https://github.com/kevinvandijk)! - Include changes from Roo Code v3.36.6 |
| 14 | + |
| 15 | + - Add tool alias support for model-specific tool customization, allowing users to configure how tools are presented to different AI models (PR #9989 by @daniel-lxs) |
| 16 | + - Sanitize MCP server and tool names for API compatibility, ensuring special characters don't cause issues with API calls (PR #10054 by @daniel-lxs) |
| 17 | + - Improve auto-approve timer visibility in follow-up suggestions for better user awareness of pending actions (PR #10048 by @brunobergher) |
| 18 | + - Fix: Cancel auto-approval timeout when user starts typing, preventing accidental auto-approvals during user interaction (PR #9937 by @roomote) |
| 19 | + - Add WorkspaceTaskVisibility type for organization cloud settings to support team visibility controls (PR #10020 by @roomote) |
| 20 | + - Fix: Extract raw error message from OpenRouter metadata for clearer error reporting (PR #10039 by @daniel-lxs) |
| 21 | + - Fix: Show tool protocol dropdown for LiteLLM provider, restoring missing configuration option (PR #10053 by @daniel-lxs) |
| 22 | + - Add: GPT-5.2 model to openai-native provider (PR #10024 by @hannesrudolph) |
| 23 | + - Fix: Handle empty Gemini responses and reasoning loops to prevent infinite retries (PR #10007 by @hannesrudolph) |
| 24 | + - Fix: Add missing tool_result blocks to prevent API errors when tool results are expected (PR #10015 by @daniel-lxs) |
| 25 | + - Fix: Filter orphaned tool_results when more results than tool_uses to prevent message validation errors (PR #10027 by @daniel-lxs) |
| 26 | + - Fix: Add general API endpoints for Z.ai provider (#9879 by @richtong, PR #9894 by @roomote) |
| 27 | + - Remove: Deprecated list_code_definition_names tool (PR #10005 by @hannesrudolph) |
| 28 | + - Add error details modal with on-demand display for improved error visibility when debugging issues (PR #9985 by @roomote) |
| 29 | + - Fix: Prevent premature rawChunkTracker clearing for MCP tools, improving reliability of MCP tool streaming (PR #9993 by @daniel-lxs) |
| 30 | + - Fix: Filter out 429 rate limit errors from API error telemetry for cleaner metrics (PR #9987 by @daniel-lxs) |
| 31 | + - Fix: Correct TODO list display order in chat view to show items in proper sequence (PR #9991 by @roomote) |
| 32 | + - Refactor: Unified context-management architecture with improved UX for better context control (PR #9795 by @hannesrudolph) |
| 33 | + - Add new `search_replace` native tool for single-replacement operations with improved editing precision (PR #9918 by @hannesrudolph) |
| 34 | + - Streaming tool stats and token usage throttling for better real-time feedback during generation (PR #9926 by @hannesrudolph) |
| 35 | + - Add versioned settings support with minPluginVersion gating for Roo provider (PR #9934 by @hannesrudolph) |
| 36 | + - Make Architect mode save plans to `/plans` directory and gitignore it (PR #9944 by @brunobergher) |
| 37 | + - Add ability to save screenshots from the browser tool (PR #9963 by @mrubens) |
| 38 | + - Refactor: Decouple tools from system prompt for cleaner architecture (PR #9784 by @daniel-lxs) |
| 39 | + - Update DeepSeek models to V3.2 with new pricing (PR #9962 by @hannesrudolph) |
| 40 | + - Add minimal and medium reasoning effort levels for Gemini models (PR #9973 by @hannesrudolph) |
| 41 | + - Update xAI models catalog with latest model options (PR #9872 by @hannesrudolph) |
| 42 | + - Add DeepSeek V3-2 support for Baseten provider (PR #9861 by @AlexKer) |
| 43 | + - Tweaks to Baseten model definitions for better defaults (PR #9866 by @mrubens) |
| 44 | + - Fix: Add xhigh reasoning effort support for gpt-5.1-codex-max (#9891 by @andrewginns, PR #9900 by @andrewginns) |
| 45 | + - Fix: Add Kimi, MiniMax, and Qwen model configurations for Bedrock (#9902 by @jbearak, PR #9905 by @app/roomote) |
| 46 | + - Configure tool preferences for xAI models (PR #9923 by @hannesrudolph) |
| 47 | + - Default to using native tools when supported on OpenRouter (PR #9878 by @mrubens) |
| 48 | + - Fix: Exclude apply_diff from native tools when diffEnabled is false (#9919 by @denis-kudelin, PR #9920 by @app/roomote) |
| 49 | + - Fix: Always show tool protocol selector for openai-compatible provider (#9965 by @bozoweed, PR #9966 by @hannesrudolph) |
| 50 | + - Fix: Respect explicit supportsReasoningEffort array values for proper model configuration (PR #9970 by @hannesrudolph) |
| 51 | + - Add timeout configuration to OpenAI Compatible Provider Client (PR #9898 by @dcbartlett) |
| 52 | + - Revert default tool protocol change from xml to native for stability (PR #9956 by @mrubens) |
| 53 | + - Improve OpenAI error messages to be more useful for debugging (PR #9639 by @mrubens) |
| 54 | + - Better error logs for parseToolCall exceptions (PR #9857 by @cte) |
| 55 | + - Improve cloud job error logging for RCC provider errors (PR #9924 by @cte) |
| 56 | + - Fix: Display actual API error message instead of generic text on retry (PR #9954 by @hannesrudolph) |
| 57 | + - Add API error telemetry to OpenRouter provider for better diagnostics (PR #9953 by @daniel-lxs) |
| 58 | + - Fix: Sanitize removed/invalid API providers to prevent infinite loop (PR #9869 by @hannesrudolph) |
| 59 | + - Fix: Use foreground color for context-management icons (PR #9912 by @hannesrudolph) |
| 60 | + - Fix: Suppress 'ask promise was ignored' error in handleError (PR #9914 by @daniel-lxs) |
| 61 | + - Fix: Process finish_reason to emit tool_call_end events properly (PR #9927 by @daniel-lxs) |
| 62 | + - Fix: Add finish_reason processing to xai.ts provider (PR #9929 by @daniel-lxs) |
| 63 | + - Fix: Validate and fix tool_result IDs before API requests (PR #9952 by @daniel-lxs) |
| 64 | + - Fix: Return undefined instead of 0 for disabled API timeout (PR #9960 by @hannesrudolph) |
| 65 | + - Stop making unnecessary count_tokens requests for better performance (PR #9884 by @mrubens) |
| 66 | + - Refactor: Consolidate ThinkingBudget components and fix disable handling (PR #9930 by @hannesrudolph) |
| 67 | + - Forbid time estimates in architect mode for more focused planning (PR #9931 by @app/roomote |
| 68 | + |
| 69 | +- [#4568](https://github.com/Kilo-Org/kilocode/pull/4568) [`b1702cd`](https://github.com/Kilo-Org/kilocode/commit/b1702cd1c3119a89c96edf23c388b84135b8cbd3) Thanks [@marius-kilocode](https://github.com/marius-kilocode)! - Remove redundant "New Agent" and "Refresh messages" buttons from agent manager session detail header. |
| 70 | + |
| 71 | +- [#4228](https://github.com/Kilo-Org/kilocode/pull/4228) [`a128228`](https://github.com/Kilo-Org/kilocode/commit/a128228b3649924ad1fd88d040a79c6963a250bd) Thanks [@lambertjosh](https://github.com/lambertjosh)! - Change the default value of auto-approval for reading outside workspace to false |
| 72 | + |
3 | 73 | ## 4.139.0 |
4 | 74 |
|
5 | 75 | ### Minor Changes |
|
0 commit comments