Release v4.125.0

4.125.0

Minor Changes

• #2827 c7793db Thanks @bea-leanix! - Added SAP AI Core provider

• #3895 f5d3459 Thanks @kevinvandijk! - Include changes from Roo Code v3.30.1-v3.32.0

  • Feature: Support for OpenAI Responses 24 hour prompt caching (PR #9259 by @hannesrudolph)
  • Fix: OpenAI Native encrypted_content handling and remove gpt-5-chat-latest verbosity flag (#9225 by @politsin, PR by @hannesrudolph)
  • Refactor: Rename sliding-window to context-management and truncateConversationIfNeeded to manageContext (thanks @hannesrudolph!)
  • Fix: Apply updated API profile settings when provider/model unchanged (#9208 by @hannesrudolph, PR by @hannesrudolph)
  • Migrate conversation continuity to plugin-side encrypted reasoning items using Responses API for improved reliability (thanks @hannesrudolph!)
  • Fix: Include mcpServers in getState() for auto-approval (#9190 by @bozoweed, PR by @daniel-lxs)
  • Batch settings updates from the webview to the extension host for improved performance (thanks @cte!)
  • Fix: Replace rate-limited badges with badgen.net to improve README reliability (thanks @daniel-lxs!)
  • Fix: Prevent command_output ask from blocking in cloud/headless environments (thanks @daniel-lxs!)
  • Fix: Model switch re-applies selected profile, ensuring task configuration stays in sync (#9179 by @hannesrudolph, PR by @hannesrudolph)
  • Move auto-approval logic from ChatView to Task for better architecture (thanks @cte!)
  • Add custom Button component with variant system (thanks @brunobergher!)
  • Improvements to to-do lists and task headers (thanks @brunobergher!)
  • Fix: Prevent crash when streaming chunks have null choices array (thanks @daniel-lxs!)
  • Fix: Prevent context condensing on settings save when provider/model unchanged (#4430 by @hannesrudolph, PR by @daniel-lxs)
  • Fix: Respect custom OpenRouter URL for all API operations (#8947 by @sstraus, PR by @roomote)
  • Fix: Auto-retry on empty assistant response to prevent task failures (#9076 by @Akillatech, PR by @daniel-lxs)
  • Fix: Use system role for OpenAI Compatible provider when streaming is disabled (#8215 by @whitfin, PR by @roomote)
  • Fix: Prevent notification sound on attempt_completion with queued messages (#8537 by @hannesrudolph, PR by @roomote)
  • Feat: Auto-switch to imported mode with architect fallback for better mode detection (#8239 by @hannesrudolph, PR by @daniel-lxs)
  • Feat: Improve diff appearance in main chat view (thanks @hannesrudolph!)
  • UX: Home screen visuals (thanks @brunobergher!)
  • Fix: eliminate UI flicker during task cancellation (thanks @daniel-lxs!)
  • Add Global Inference support for Bedrock models (#8750 by @ronyblum, PR by @hannesrudolph)
  • Add Qwen3 embedding models (0.6B and 4B) to OpenRouter support (#9058 by @dmarkey, PR by @app/roomote)
  • Fix: keep pinned models fixed at top of scrollable list (#8812 by @XiaoYingYo, PR by @app/roomote)
  • Fix: update Opus 4.1 max tokens from 8K to 32K (#9045 by @kaveh-deriv, PR by @app/roomote)
  • Set Claude Sonnet 4.5 as default for key providers (thanks @hannesrudolph!)
  • Fix: dynamic provider model validation to prevent cross-contamination (#9047 by @NotADev137, PR by @daniel-lxs)
  • Fix: Bedrock user agent to report full SDK details (#9031 by @ajjuaire, PR by @ajjuaire)
  • Add file path tooltips with centralized PathTooltip component (#8278 by @da2ce7, PR by @daniel-lxs)
  • Fix: Correct OpenRouter Mistral model embedding dimension from 3072 to 1536 (thanks @daniel-lxs!)

• #3868 cf6ed3e Thanks @iscekic! - add sessions support

Patch Changes

• #4059 d47a3d5 Thanks @chrarnoldus! - Fix error on task resumption with some providers when native tool calls are enabled

• #3565 4a05694 Thanks @marcus-v-rodrigues! - Fix 403 error for Gemini CLI by removing 'default' project fallback

• #2540 591da2b Thanks @gerardbalaoro! - Support for MCP servers in .cursor/mcp.json

• #2324 ab9b94b Thanks @mikkihugo! - Add VS Code Settings Sync integration

• #3193 6a895de Thanks @siulong! - Fix rules folder path when deleting the rules

• #3804 5d4b38b Thanks @skridlevsky! - fix(settings): codebase indexing toggle not persisting

• #3484 ac01ae3 Thanks @mental-lab! - Add warning for ANTHROPIC_API_KEY conflicts with Claude Code provider

• #3087 ebab11b Thanks @jinhan1414! - Unify slash command parsing and expand mention detection

Release v4.124.0

4.124.0

Minor Changes

• #2587 f3de1e7 Thanks @NaccOll! - Add LanceDB vector store support

Patch Changes

• #4045 b14afb1 Thanks @eshurakov! - Nano GPT provider support (by @b3nw)

• #4023 5af4d01 Thanks @markijbema! - Small redesign of the autocomplete statusbar/tooltip

Release v4.123.0

4.123.0

Minor Changes

• #3020 147786c Thanks @CaiDingxian! - Add independent provider setup for Fast Apply feature

Patch Changes

• #4019 f16c31b Thanks @chrarnoldus! - Add Opus 4.5 to Claude Code provider

• #3445 8065f7a Thanks @jeanduplessis! - fix: apply file limit after .kilocodeignore filtering instead of before

• #3988 a169e6f Thanks @dltechy! - Fix an issue where workflows are not working except as the initial prompt of a task

Release v4.122.1

4.122.1

Patch Changes

• #4000 3ef2237 Thanks @brianc! - There was previously some debug log spam introduced for the Managed Indexing feature. This change removes those logs.

• #4005 5aa56df Thanks @chrarnoldus! - Add Claude Opus 4.5 support, including verbosity controls for Kilo Gateway, OpenRouter and Anthropic providers

Release v4.122.0

4.122.0

Minor Changes

• #3609 65191fd Thanks @mcowger! - Synthetic provider to use updated models endpoint and dynamic fetcher

• #3674 cdd439a Thanks @mental-lab! - Kilo Code can now delete files and directories without using command line tools.

Patch Changes

• #3925 02abc84 Thanks @jrf0110! - Improve organization/managed indexing performance

Release v4.121.2

4.121.2

Patch Changes

• #3951 1f4f9bd Thanks @chrarnoldus! - Add Gemini 3 Pro Image Preview

• #3879 d07e192 Thanks @Maosghoul! - Optimized MiniMax M2 interleaved thinking by merging environment details into tool results.

• #3939 189aee3 Thanks @ajspetner! - Added grok-4-1-fast-reasoning and grok-4-1-fast-non-reasoning models

Release v4.121.1

[v4.121.1]

• #3601 eaf1f5a Thanks @hassoncs! - Now items in the Chat context menu will not be auto selected if your cursor is already on the row when the items change

• #3915 c096af9 Thanks @chrarnoldus! - Improve file edit success rates for non-Claude models with native tool calling

• #3912 6036695 Thanks @markijbema! - Do not show browser window when closing the browser

• #3911 ae8f4c7 Thanks @markijbema! - Fixed model search, now finds gemini again

Release v4.121.0

[v4.121.0]

• #3886 00e6fb5 Thanks @catrielmuller! - Improve XLSX support

Patch Changes

• #3872 75509af Thanks @ShivamB25! - Update default Gemini model to gemini-3-pro-preview

• #3878 7b01fc8 Thanks @markijbema! - Fix manual configuration in welcome flow

Release v4.120.0

[v4.120.0]

• #3778 b9a9f70 Thanks @markijbema! - Made the dropdown searches more intuitive, search like vscode does

Patch Changes

• #3867 23b805b Thanks @kevinvandijk! - Add Gemini 3 Pro Preview to Gemini and Vertex providers (thanks @Sn0wo2!)

• #3832 9d77cb1 Thanks @chrarnoldus! - Reduced the incidence of unsuccessful edits with MiniMax M2

Release v4.119.6

[v4.119.6]

• #3836 b5cf145 Thanks @mcowger! - Add GPT-5.1 models for OpenAI provider

• #3732 c75dd9f Thanks @markijbema! - When editting a profile is the settings, do not implicitly switch to that profile

• #3793 20f0b71 Thanks @chrarnoldus! - Default GPT 5.x Codex to JSON style tool calls