Release history
Kimi Code 2.3.0
Model switching now prompts for session handling, plugin skills use qualified names, remote control supports 100 MiB transfers, multi-client sessions handle conflicts, and auto-generated titles appear in terminal windows
Kimi Code 2.2.0
Kimi Code 2.2.0 adds agent progress notifications, Tower mode deterministic orchestration, 90-second task wait caps, and sticky message summaries for faster navigation
Kimi Code 2.0.2
Kimi Code 2.0.2 fixes conversation state bugs, context window switching failures, working directory detection, and duplicate message display issues
Kimi Code 2.0.1
Kimi Code 2.0.1 improves CLI startup and session loading performance, adds environment variable API key support, and fixes media tool listings and session message duplication
Kimi Code 0.43.1
Fixes memory leaks, rendering performance, and subagent lifecycle issues while improving terminal UI and clipboard support on Linux
Kimi Code 0.43.0
AI sessions now auto-generate titles, session deletion added, and UI stability improved for long conversations and complex content rendering
Kimi Code 0.42.0
Subagent model pool now always enabled, experimental Updates panel added, media previews in composer, and tool-call output collapsing for cleaner transcripts
Kimi Code 0.41.0
Kimi Code adds multi-agent collaboration mode, enables turn-level file history, and improves context management and background agent workflows
Kimi Code 0.40.0
Kimi Code 0.40.0 enables secondary model pool, adds plugin marketplace in web settings, blocks dangerous shell commands in Auto mode, and fixes config preservation and UI rendering issues
Kimi Code 0.37.2
Kimi Code 0.37.2 expands subagent detail panels and adds optional multi-tab sidebar navigation in Settings Lab
Kimi Code 0.36.0
Experimental fullscreen TUI mode, configurable model pools for subagents, LaTeX rendering, improved interrupt handling, and workspace trust enhancements
Kimi Code 0.35.0
Tasks panel now displays live subagent progress, image/video results open in fullscreen with zoom, token counting fixed, and startup freezes from search index loading eliminated
Kimi Code 0.34.0
Kimi Code adds Windows Computer Use support, persistent failure cards with one-click resume, and cache-expiry reminders for idle sessions
Kimi Code 0.33.0
CLI now runs on agent-core-v2 engine, adds Computer Use and WebBridge to marketplace, and improves session forking and trust prompts
Kimi Code 0.32.0
Kimi Code 0.32.0 adds hook events for session lifecycle tracking, offline model catalog fallback, renames loop control config keys, and fixes tool call ID parsing with colon-containing provider responses
Kimi Code 0.31.1
Fixes model catalog initialization race, preserves interrupted outputs, enables Monaco code highlighting, improves TUI performance, and corrects permission ordering and chat rendering bugs
Kimi Code 0.31.0
Kimi Code adds plugin-contributed custom agents with Markdown definitions, configurable system prompts, and sub-agent delegation, plus fixes for request headers and task blocking
Kimi Code 0.30.0
Customizable footer status line, halted retries on invalid tool calls, quota warnings for plugins, fast-fail on account exhaustion, and removed file upload size limits
Kimi Code 0.29.2
Kimi Code 0.29.2 fixes goal interruption, message handling during active goals, chat copying over HTTP, and /undo consistency; Defers tool schema registration and improves runtime state management
Kimi Code 0.29.1
Kimi Code 0.29.1 adds MCP server timeouts, fixes reasoning field detection for OpenAI-compatible endpoints, and enables web search/fetch configuration via environment variables
Kimi Code 0.29.0
Kimi Code 0.29.0 adds granular thinking effort levels in ACP clients, custom Markdown-based agents with tool gating, video attachment support, and raw file serving via API
Kimi Code 0.28.1
ACP sessions now accept pre-configured model credentials, web servers run foreground-only, and subagents respect runtime permission changes
Kimi Code 0.28.0
Replaced kimi server with kimi web for foreground operation and multi-instance support sharing one home directory, fixed permission mode descriptions, and enabled symlink handling in agent file loading
Kimi Code 0.25.0
Chat now accepts any file type, uploading unconsumed files to server for model access, plus fixes for authentication bypass, symlink traversal, Anthropic thinking controls, and CSP issues
Kimi Code 0.24.1
Kimi Code fixes session hangs from empty reasoning steps, corrects tool availability timing, improves thinking-level persistence and UI display across web and CLI
Kimi Code 0.24.0
Kimi Code 0.24.0 defaults local server to agent-core-v2 engine, handles long-running commands via backgrounding instead of killing, and adds session diagnostic export
Kimi Code 0.23.6
Dismissed prompts now treated as non-answers, print-mode sessions survive background tasks and active goals, subagent timeouts extended to 2 hours and made configurable, web UI connection and scrolling fixes
Kimi Code 0.23.4
Kimi Code adds fuel-pack balance display, fixes session resumption and prompt-goal execution, implements image compression with configurable size limits to prevent request failures, and improves web UI reliability and styling
Kimi Code 0.23.1
Kimi Code 0.23.1 fixes goal token budgets, WebSocket reconnection, background subagent handling, and Claude thinking preservation on Anthropic providers
Kimi Code 0.23.0
Preserved thinking enabled, progressive tool disclosure for prompt caching, archived session management, and improved user question feedback in AskUserQuestion
Kimi Code 0.20.2
Adds optional API parameter to exclude empty sessions from the session list
Kimi Code 0.19.1
Fixes ACP editor thread initialization, clears orphaned session data on archive, syncs unread indicators across browser tabs, and refactors web client state management