@moonshot-ai/kimi-code@0.21.0

Minor Changes

• #1204 5cb80ce - Plugins can now provide slash commands via a commands field in their manifest, registered as <plugin>:<command> and invoked with $ARGUMENTS expansion.

• #1214 86e0c92 - Rework conversation compaction:

  • Keep only recent user prompts plus a single user-role summary; drop assistant and tool messages.
  • Repair tool_use/tool_result adjacency before sending, fixing a strict-provider HTTP 400 when a tool call and its result became non-adjacent.
  • Merge consecutive user turns for strict providers (Gemini/Vertex), fixing an HTTP 400 ("roles must alternate") after compaction or when a turn is steered in right after a tool result.
  • Micro-compaction now defaults off.

• #1132 108299b - Refactor the thinking effort system

Patch Changes

• #1231 ceb27f5 - Add a server-side key-value store API for persisting web UI preferences to the user's data directory.

• #1220 ec51324 - Add a double-Esc shortcut to open the undo selector. Press Esc twice while idle to undo.

• #1223 80e6888 - Fix @ file mentions not opening when typed inside a slash command argument.

• #1233 020992c - Force-exit headless runs (kimi -p) so a stray ref'd handle left over from the run can't keep a completed run alive until an external timeout, and bound prompt cleanup so a wedged shutdown step can't hang shutdown.

• #1225 659062d - Show file path completions when typing / in shell mode (!).

• #1236 bfe8e6a - Fix adding a workspace by path in the web UI failing silently when the daemon rejects the path; it now shows an error instead of a broken workspace.

• #1221 a3f9cec - Fix duplicate workspaces showing in the web sidebar when the same folder is registered more than once.

• #1241 8ac337a - Stop a malformed message history from permanently bricking a session on strict providers (Anthropic). The request is repaired before sending — orphaned tool calls are closed and empty/whitespace-only text blocks dropped — and if the provider still rejects its structure, it is resent once with a wire-compliant rebuild.

• #1228 42e37eb - Split LLM streaming timing in the session log and KIMI_CODE_DEBUG=1 output into client vs. API-server portions, so slow turns can be attributed without parsing the wire log. Time-to-first-token splits into the API-server portion (network + server) and the client portion (in-process request building); the decode window splits into time awaiting tokens from the server and time the client spends processing each streamed chunk.

• #1234 882cf35 - Hide the provider management dialog in the web UI until the server supports it.

• #1226 7f05f58 - Add Mermaid diagram rendering to the web chat. Fenced mermaid blocks in assistant responses now render as diagrams. KaTeX math and Mermaid diagram parsing also run in Web Workers to keep the UI responsive during live streaming.

• #1232 aa6b0d0 - Always show the usage-data opt-out toggle in the web settings with a clearer label and description.

• #1234 882cf35 - Fix the web workspace rename not persisting after a page refresh.