Release v4.91.0

[v4.91.0]

• #2289 13c45e5 Thanks @chrarnoldus! - Added support for Kimi K2 0905 to Chutes, Fireworks, Groq and Moonshot providers

• #2294 980a253 Thanks @catrielmuller! - Jetbrains - MultiDiff / See New Changes support

Patch Changes

• #2281 71334fc Thanks @hassoncs! - Clear images when changing to a model that does not support them

• #2280 0713b0d Thanks @hassoncs! - Fix organization switching not saving properly

• #2287 b5a8550 Thanks @Qiiks! - Fix Gemini CLI integration to handle nested response structures

Release v4.90.0

[v4.90.0]

• #2275 4ae9acc Thanks @jeske! - fixes an intermittent async race that discards user-chat-input during structured approve/reject

• #2129 984b5c4 Thanks @catrielmuller! - Jetbrains Extension Beta

Patch Changes

• #2274 24d0c9f Thanks @chrarnoldus! - The API Provider (Kilo Code or OpenRouter) for image generation is now an explicit choice

Release v4.89.0

[v4.89.0]

• #2242 f474c89 Thanks @kevinvandijk! - Include changes from Roo Code v3.26.4

  • Optimize memory usage for image handling in webview (thanks @daniel-lxs!)
  • Fix: Special tokens should not break task processing (#7539 by @pwilkin, PR by @pwilkin)
  • Add Ollama API key support for Turbo mode (#7147 by @LivioGama, PR by @app/roomote)
  • Add optional input image parameter to image generation tool (thanks @roomote!)
  • Refactor: Flatten image generation settings structure (thanks @daniel-lxs!)
  • Show console logging in vitests when the --no-silent flag is set (thanks @hassoncs!)
  • feat: Add experimental image generation tool with OpenRouter integration (thanks @daniel-lxs!)
  • Fix: Resolve GPT-5 Responses API issues with condensing and image support (#7334 by @nlbuescher, PR by @daniel-lxs)
  • Fix: Hide .kilocodeignore'd files from environment details by default (#7368 by @AlexBlack772, PR by @app/roomote)
  • Fix: Exclude browser scroll actions from repetition detection (#7470 by @cgrierson-smartsheet, PR by @app/roomote)
  • Add Vercel AI Gateway provider integration (thanks @joshualipman123!)
  • Add support for Vercel embeddings (thanks @mrubens!)
  • Enable on-disk storage for Qdrant vectors and HNSW index (thanks @daniel-lxs!)
  • Update tooltip component to match native VSCode tooltip shadow styling (thanks @roomote!)
  • Fix: remove duplicate cache display in task header (thanks @mrubens!)
  • Random chat text area cleanup (thanks @cte!)
  • feat: Add Deepseek v3.1 to Fireworks AI provider (#7374 by @dmarkey, PR by @app/roomote)
  • Fix: Make auto approve toggle trigger stay (#3909 by @kyle-apex, PR by @elianiva)
  • Fix: Preserve user input when selecting follow-up choices (#7316 by @teihome, PR by @daniel-lxs)
  • Fix: Handle Mistral thinking content as reasoning chunks (#6842 by @Biotrioo, PR by @app/roomote)
  • Fix: Resolve newTaskRequireTodos setting not working correctly (thanks @hannesrudolph!)
  • Fix: Requesty model listing (#7377 by @dtrugman, PR by @dtrugman)
  • feat: Hide static providers with no models from provider list (thanks @daniel-lxs!)
  • Add todos parameter to new_task tool usage in issue-fixer mode (thanks @hannesrudolph!)
  • Handle substitution patterns in command validation (thanks @mrubens!)
  • Mark code-workspace files as protected (thanks @mrubens!)
  • Update list of default allowed commands (thanks @mrubens!)
  • Follow symlinks in rooignore checks (thanks @mrubens!)
  • Show cache read and write prices for OpenRouter inference providers (thanks @chrarnoldus!)

Release v4.88.0

[v4.88.0]

• #2235 fbf4e42 Thanks @catrielmuller! - Rename Inline Assist to Kilo Code Autocomplete

• #2202 92ef190 Thanks @hassoncs! - Show a warning when trying to paste an image when the current model does not support images

Patch Changes

• #2244 6a83c5a Thanks @hassoncs! - Prevent writing to files outside the workspace by default

  This should mitigate supply chain compromise attacks via prompt injection. Thank you, Evan Harris from MCP Security Research for finding this!

• #2245 fff884f Thanks @hassoncs! - Fix Kilo Code Marketplace header missing background color

• #2237 06c6e8b Thanks @chrarnoldus! - Kilo Code now shows an error message when a model reaches its maximum ouput

• #2238 b5de938 Thanks @chrarnoldus! - Fixed 500 error with Chutes when no custom temperature is specified.

• #2248 b8c6f27 Thanks @hassoncs! - Remove the Inline Assist experiment, enabling it by default

  The individual commands and keyboard shortcuts can still be enabled/disabled individually in the settings.

Release v4.87.0

[v4.87.0]

• #2010 a7b89d3 Thanks @chrarnoldus! - There is now a "See New Changes" button below a Task Completed message. Use this button to see all file changes made since the previous Task Completed message. This feature requires checkpoints to be enabled.

Patch Changes

• #2215 4b102aa Thanks @chrarnoldus! - The Data Provider Collection setting in the Kilo Code and OpenRouter provider settings is now enabled even when a specific inference provider is selected.

• #2228 5bd17b9 Thanks @chrarnoldus! - Warning messages for common cases where checkpoints do not work were added

• #2174 a1d0972 Thanks @TimAidley! - Add GPT-5 support to LiteLLM provider

• #2216 479821f Thanks @chrarnoldus! - The OLLAMA_CONTEXT_LENGTH environment variable is now prioritized over the model's num_ctx parameter.

• #2191 6fcde72 Thanks @hassoncs! - Explicitly disable the web version of the extension since it is not compatible (vscode.dev)

Release v4.86.0

[v4.86.0]

• #2012 1fd698a Thanks @catrielmuller! - Improve Inline Assist model compatibility and performance

• #2199 a19f72c Thanks @chrarnoldus! - Thanks @Thachnh! - Added DeepInfra provider with dynamic model fetching and prompt caching

Patch Changes

• #2170 58987e3 Thanks @mcowger! - Remove the forced override of the context limit for Ollama API

Release v4.85.0

[v4.85.0]

• #2119 19dc45d Thanks @kevinvandijk! - Include changes from Roo Code v3.25.23

  • feat: add custom base URL support for Requesty provider (thanks @requesty-JohnCosta27!)
  • feat: add DeepSeek V3.1 model to Chutes AI provider (#7294 by @dmarkey, PR by @app/roomote)
  • Add prompt caching support for Kimi K2 on Groq (thanks @daniel-lxs and @benank!)
  • Add documentation links for global custom instructions in UI (thanks @app/roomote!)
  • Ensure subtask results are provided to GPT-5 in OpenAI Responses API
  • Promote the experimental AssistantMessageParser to the default parser
  • Update DeepSeek models context window to 128k (thanks @JuanPerezReal)
  • Enable grounding features for Vertex AI (thanks @anguslees)
  • Allow orchestrator to pass TODO lists to subtasks
  • Improved MDM handling
  • Handle nullish token values in ContextCondenseRow to prevent UI crash (thanks @s97712)
  • Improved context window error handling for OpenAI and other providers
  • Add "installed" filter to Marketplace (thanks @semidark)
  • Improve filesystem access checks (thanks @elianiva)
  • Add Featherless provider (thanks @DarinVerheijke)

Patch Changes

• #2184 0be6743 Thanks @kevinvandijk! - Fix: add favorite button back to tasks

• #2125 5828254 Thanks @nitinprajwal! - Added support to Qwen Code for a custom OAuth credential storage path

Release v4.84.1

[v4.84.1]

• #2113 d40b35a Thanks @chrarnoldus! - The model selector below the chat now shows the correct model list for Qwen Code and some other providers

• #2116 61e18d6 Thanks @chrarnoldus! - Checkpoints now work when using Morph fast apply

• #2130 78aaf7c Thanks @chrarnoldus! - Added support for Grok Code Fast to the xAI provider

• #2109 173ecf4 Thanks @chrarnoldus! - A solitary "0" that was sometimes shown on the Kilo Code and OpenRouter API provider settings page was removed.

Release v4.84.0

[v4.84.0]

• #1961 d4a7cb6 Thanks @chrarnoldus! - Updates to the experimental Morph FastApply support

  • A visual indication is now included in the task view whenever Morph is used.
  • The traditional file editing tools are now disabled to ensure Morph is used to edit files.
  • Morph is now automatically disabled when the API provider does not support it and no Morph API key is configured.
  • The Morph API key is no longer lost when switching provider profiles.

• #1886 0221aaa Thanks @mcowger! - Add collapsible MCP tool calls with memory management

Patch Changes

• #2095 8623bb8 Thanks @chrarnoldus! - Kilo Code provider now falls back to the default model when the selected model no longer exists

• #2090 fd147b8 Thanks @Mats4k! - Improvements to German language translation

• #2030 11e8c7d Thanks @ivanarifin! - Show message when Virtual Quota Fallback Provider switches profiles

• #2100 5ed3d7b Thanks @RSO! - Changed the API domain for the Kilo Code provider

• #1964 6b0dfbf Thanks @chrarnoldus! - The Kilo Code API Provider settings now also shows the average cost per request in addition to the average cost per million tokens for a particular model.

Release v4.83.1

[v4.83.1]

• #2073 a4b8770 Thanks @chrarnoldus! - Ensured free model usage is reported as free

• #2066 62624d2 Thanks @mcowger! - Fixed "'messages' field is required" error in LMStudio

• #2064 8655a71 Thanks @chrarnoldus! - Improved the "language model did not provide any assistant messages" error message to indicate that it likely involves rate limiting