Release v4.140.3

4.140.3

Patch Changes

• #4648 4710d11 Thanks @marius-kilocode! - Fix Agent Manager multi-version sessions to wait for pending CLI processes so terminals are available per worktree.

• #4658 e189583 Thanks @marius-kilocode! - Improve Agent Manager telemetry

• #4647 c1a0692 Thanks @marius-kilocode! - fix: reduce GPU usage in Agent Manager with message virtualization

• #4693 eb5e835 Thanks @keeganwitt! - Add Requesty Codestral to autocomplete provider models

• #4659 fa42cfa Thanks @marius-kilocode! - Fix Agent Manager CLI detection and Windows spawn by sanitizing shell output and running .cmd via cmd.exe.

• #4692 1401220 Thanks @mcowger! - Fix loss of Synthetic auto model refresh

Release v4.140.2

4.140.2

Patch Changes

• #4628 ab0085e Thanks @kiloconnect! - Add GLM-4.7 model support to Z.ai provider

• #4622 25de94b Thanks @alvinward! - Added model selection support below prompt for Z.ai

• #4637 b47994f Thanks @chrarnoldus! - Add MiniMax-M2.1 model for MiniMax provider

Release v4.140.1

4.140.1

Patch Changes

• #4615 6909640 Thanks @marius-kilocode! - Add Agent Manager terminal switching so existing session terminals are revealed when changing sessions.

• #4586 a3988cd Thanks @marius-kilocode! - Fix Agent Manager failing to start on macOS when launched from Finder/Spotlight

• #4561 3c18860 Thanks @jrf0110! - Introduces AI contribution tracking so users can better understand agentic coding impact

• #4526 10b4d6c Thanks @chrarnoldus! - Reduce the incidence of read_file errors when using Claude models.

• #4560 5bdfe6b Thanks @crazyrabbit0! - chore: update Gemini Cli models and metadata

  • Added gemini-3-flash-preview model configuration.
  • Updated maxThinkingTokens for gemini-3-pro-preview to 32,768.
  • Reordered model definitions to prioritize newer versions.

• #4596 1c33884 Thanks @hank9999! - Fix duplicate tool use in Anthropic

• #4620 ae6818b Thanks @chrarnoldus! - Fix duplictate tool call processing in Chutes, DeepInfra, LiteLLM and xAI providers.

• #4597 e2bb5c1 Thanks @marius-kilocode! - Fix Agent Manager not showing error when CLI is misconfigured. When the CLI exits with a configuration error (e.g., missing kilocodeToken), the extension now detects this and shows an error popup with options to run kilocode auth or kilocode config.

• #4590 f2cc065 Thanks @kiloconnect! - feat: add session_title_generated event emission to CLI

• #4523 e259b04 Thanks @markijbema! - Add chat autocomplete telemetry

• #4582 3de2547 Thanks @catrielmuller! - Jetbrains - Autocomplete Telemetry

• #4488 f7c3715 Thanks @lifesized! - fix(ollama): fix model not found error and context window display

Release CLI - v0.18.0

0.18.0

Minor Changes

• #4583 845f8c1 Thanks @kiloconnect! - Add markdown theming support for Reasoning box content

Patch Changes

• #4590 f2cc065 Thanks @kiloconnect! - feat: add session_title_generated event emission to CLI

Release v4.140.0

4.140.0

Minor Changes

• #4538 459b95c Thanks @chrarnoldus! - Added gemini-3-flash-preview model

Patch Changes

• #4530 782347e Thanks @alvinward! - Add GLM-4.6V model support for z.ai provider

• #4509 8a9fddd Thanks @kevinvandijk! - Include changes from Roo Code v3.36.6

  • 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)
  • Sanitize MCP server and tool names for API compatibility, ensuring special characters don't cause issues with API calls (PR #10054 by @daniel-lxs)
  • Improve auto-approve timer visibility in follow-up suggestions for better user awareness of pending actions (PR #10048 by @brunobergher)
  • Fix: Cancel auto-approval timeout when user starts typing, preventing accidental auto-approvals during user interaction (PR #9937 by @roomote)
  • Add WorkspaceTaskVisibility type for organization cloud settings to support team visibility controls (PR #10020 by @roomote)
  • Fix: Extract raw error message from OpenRouter metadata for clearer error reporting (PR #10039 by @daniel-lxs)
  • Fix: Show tool protocol dropdown for LiteLLM provider, restoring missing configuration option (PR #10053 by @daniel-lxs)
  • Add: GPT-5.2 model to openai-native provider (PR #10024 by @hannesrudolph)
  • Fix: Handle empty Gemini responses and reasoning loops to prevent infinite retries (PR #10007 by @hannesrudolph)
  • Fix: Add missing tool_result blocks to prevent API errors when tool results are expected (PR #10015 by @daniel-lxs)
  • Fix: Filter orphaned tool_results when more results than tool_uses to prevent message validation errors (PR #10027 by @daniel-lxs)
  • Fix: Add general API endpoints for Z.ai provider (#9879 by @richtong, PR #9894 by @roomote)
  • Remove: Deprecated list_code_definition_names tool (PR #10005 by @hannesrudolph)
  • Add error details modal with on-demand display for improved error visibility when debugging issues (PR #9985 by @roomote)
  • Fix: Prevent premature rawChunkTracker clearing for MCP tools, improving reliability of MCP tool streaming (PR #9993 by @daniel-lxs)
  • Fix: Filter out 429 rate limit errors from API error telemetry for cleaner metrics (PR #9987 by @daniel-lxs)
  • Fix: Correct TODO list display order in chat view to show items in proper sequence (PR #9991 by @roomote)
  • Refactor: Unified context-management architecture with improved UX for better context control (PR #9795 by @hannesrudolph)
  • Add new search_replace native tool for single-replacement operations with improved editing precision (PR #9918 by @hannesrudolph)
  • Streaming tool stats and token usage throttling for better real-time feedback during generation (PR #9926 by @hannesrudolph)
  • Add versioned settings support with minPluginVersion gating for Roo provider (PR #9934 by @hannesrudolph)
  • Make Architect mode save plans to /plans directory and gitignore it (PR #9944 by @brunobergher)
  • Add ability to save screenshots from the browser tool (PR #9963 by @mrubens)
  • Refactor: Decouple tools from system prompt for cleaner architecture (PR #9784 by @daniel-lxs)
  • Update DeepSeek models to V3.2 with new pricing (PR #9962 by @hannesrudolph)
  • Add minimal and medium reasoning effort levels for Gemini models (PR #9973 by @hannesrudolph)
  • Update xAI models catalog with latest model options (PR #9872 by @hannesrudolph)
  • Add DeepSeek V3-2 support for Baseten provider (PR #9861 by @AlexKer)
  • Tweaks to Baseten model definitions for better defaults (PR #9866 by @mrubens)
  • Fix: Add xhigh reasoning effort support for gpt-5.1-codex-max (#9891 by @andrewginns, PR #9900 by @andrewginns)
  • Fix: Add Kimi, MiniMax, and Qwen model configurations for Bedrock (#9902 by @jbearak, PR #9905 by @app/roomote)
  • Configure tool preferences for xAI models (PR #9923 by @hannesrudolph)
  • Default to using native tools when supported on OpenRouter (PR #9878 by @mrubens)
  • Fix: Exclude apply_diff from native tools when diffEnabled is false (#9919 by @denis-kudelin, PR #9920 by @app/roomote)
  • Fix: Always show tool protocol selector for openai-compatible provider (#9965 by @bozoweed, PR #9966 by @hannesrudolph)
  • Fix: Respect explicit supportsReasoningEffort array values for proper model configuration (PR #9970 by @hannesrudolph)
  • Add timeout configuration to OpenAI Compatible Provider Client (PR #9898 by @dcbartlett)
  • Revert default tool protocol change from xml to native for stability (PR #9956 by @mrubens)
  • Improve OpenAI error messages to be more useful for debugging (PR #9639 by @mrubens)
  • Better error logs for parseToolCall exceptions (PR #9857 by @cte)
  • Improve cloud job error logging for RCC provider errors (PR #9924 by @cte)
  • Fix: Display actual API error message instead of generic text on retry (PR #9954 by @hannesrudolph)
  • Add API error telemetry to OpenRouter provider for better diagnostics (PR #9953 by @daniel-lxs)
  • Fix: Sanitize removed/invalid API providers to prevent infinite loop (PR #9869 by @hannesrudolph)
  • Fix: Use foreground color for context-management icons (PR #9912 by @hannesrudolph)
  • Fix: Suppress 'ask promise was ignored' error in handleError (PR #9914 by @daniel-lxs)
  • Fix: Process finish_reason to emit tool_call_end events properly (PR #9927 by @daniel-lxs)
  • Fix: Add finish_reason processing to xai.ts provider (PR #9929 by @daniel-lxs)
  • Fix: Validate and fix tool_result IDs before API requests (PR #9952 by @daniel-lxs)
  • Fix: Return undefined instead of 0 for disabled API timeout (PR #9960 by @hannesrudolph)
  • Stop making unnecessary count_tokens requests for better performance (PR #9884 by @mrubens)
  • Refactor: Consolidate ThinkingBudget components and fix disable handling (PR #9930 by @hannesrudolph)
  • Forbid time estimates in architect mode for more focused planning (PR #9931 by @app/roomote

• #4568 b1702cd Thanks @marius-kilocode! - Remove redundant "New Agent" and "Refresh messages" buttons from agent manager session detail header.

• #4228 a128228 Thanks @lambertjosh! - Change the default value of auto-approval for reading outside workspace to false

Release CLI - v0.17.1

0.17.1

Patch Changes

• #4186 6078a9c Thanks @lambertjosh! - Default read permissions now require approval for read operations outside the workspace

Release v4.139.0

4.139.0

Minor Changes

• #4481 61c951c Thanks @marius-kilocode! - Improved command output rendering in Agent Manager with new CommandExecutionBlock component that displays terminal output with status indicators, collapsible output sections, and proper escape sequence handling.

• #4483 fd639ab Thanks @marius-kilocode! - Add branch picker to Agent Manager for selecting base branch in worktree mode

• #4539 62a0241 Thanks @brianc! - Improve managed indexer error handling & backoff.

Patch Changes

• #4512 f979b56 Thanks @hassoncs! - Add a tooltip explaining why speech-to-text may be unavailable

• #4424 cd0cd88 Thanks @markijbema! - Added a snooze for autocomplete in the settings

• #4519 a9fd203 Thanks @chrarnoldus! - Fix text.startsWith is not a function crash

• #4536 51f4774 Thanks @kevinvandijk! - Fix image generation handler not using Kilo Gateway properly

• #4491 823b86f Thanks @markijbema! - Prevent autocomplete from showing suggestions duplicating the previous or next line

• #4531 9413d73 Thanks @chrarnoldus! - Fix duplicate tool processing in OpenAI-compatible provider

• #4533 20b2c29 Thanks @mcowger! - Add gemini-3-flash-preview model configuration to vertex models

• #4520 8342fc4 Thanks @chrarnoldus! - Normalize line endings in search and replace tool

Release v4.138.0

4.138.0

Minor Changes

• #4472 d2e82a1 Thanks @marius-kilocode! - Interactive agent manager worktree sessions now start without auto-execution, allowing to manually click "Finish to Branch".

• #4428 8394da8 Thanks @iscekic! - add parent session id when creating a session

Patch Changes

• #4425 6f70448 Thanks @marius-kilocode! - Share kilocode extension authentication directly with agent manager

• #4475 625561f Thanks @jrf0110! - Fixes issue on Windows where kilo code would spawn many cmd.exe windows.

• #4376 3971db3 Thanks @sebastiand-cerebras! - Add Cerebras integration header with "kilocode" identifier to all API requests.

• #4447 0022305 Thanks @EamonNerbonne! - Provide a few tips for when an LLM gets stuck in a loop

• #4456 85a2e31 Thanks @iscekic! - correctly handle deleted tasks

• #4476 ea9413d Thanks @hassoncs! - Remove check for ffmpeg if the STT experiment is disabled

Release v4.137.0

4.137.0

Minor Changes

• #4394 01b968b Thanks @hassoncs! - Add Speech-To-Text experiment for the chat input powered by ffmpeg and the OpenAI Whisper API

• #4388 af93318 Thanks @iscekic! - send org id and last mode with session data

Patch Changes

• #4412 d56879c Thanks @quantizoor! - Added support for xhigh reasoning effort

• #4415 5e670d1 Thanks @kevinvandijk! - Fix: bottom controls no longer overlap with create mode button

• #4416 026da65 Thanks @marius-kilocode! - fix: resolve AbortSignal memory leak in CLI (MaxListenersExceededWarning)

• #4392 73681e9 Thanks @markijbema! - Split autocomplete suggestion in current line and next lines in most cases

• #4426 fdc0c0a Thanks @kevinvandijk! - Fix API request errors with MCP functions incompatible with OpenAI strict mode

• #4373 a80ec02 Thanks @marius-kilocode! - Handle different cli authentication errors when using agent manager

Release CLI - v0.16.0

0.16.0

Minor Changes

• #4388 af93318 Thanks @iscekic! - send org id and last mode with session data