Kimi Code 0.3.0

0.3.0Desktop
Changed 6
  • /logout now opens a picker to choose which provider to log out of, with the current provider highlighted by default, and is also available as /disconnect
  • Todo panel is hidden on resume when all todos are already completed
  • Improve the Write tool UX
  • Prevent running the /model and /sessions slash commands while streaming or compacting context
  • OpenAI-compatible reasoner models now work out of the box with auto-detection of thinking fields, serialization as reasoning_content, and auto-injection of reasoning_effort, eliminating the need for hand-set reasoning_key for services like DeepSeek and Qwen
  • Avoid overly small local completion caps that can truncate reasoning before summaries are produced
Fixed 7
  • API key input dialog no longer shows a masked dot in empty state
  • User skills in ~/.agents/ are now loaded correctly
  • Real-time token display for running subagents in the TUI is restored
  • Always emit a paired tool result when a tool returns a malformed or missing result to prevent the next request from failing with a missing tool_call_id error
  • Plan mode session resets so new sessions no longer fail after plan review rejection and continue receiving events after setup errors
  • Exit promptly when the controlling terminal goes away by handling SIGHUP, SIGTERM, and stdout/stderr I/O errors to prevent leftover processes
  • Preserve catalog-declared interleaved reasoning fields for OpenAI-compatible models configured through /connect
Minor Changes
  • #76 6f22ae4 - /logout now opens a picker so you can choose which provider to log out of, instead of always logging out the one tied to the current model. The current provider is highlighted by default, so pressing Enter matches the previous behavior. The command is also available as /disconnect.
Patch Changes

  • #62 e2b2b46 - Make AgentRecords hold the Agent instance directly and inline the restore dispatch logic.

  • #73 bddc60f - Prevent running the /model and /sessions slash commands while streaming or compacting context.

  • #70 d95b013 - Preserve catalog-declared interleaved reasoning fields for OpenAI-compatible models configured through /connect.

  • #78 61f7d0e - Make OpenAI-compatible reasoner models work out of the box for hand-written provider configs. The openai provider now auto-detects thinking on incoming responses by scanning the de facto field set (reasoning_content, reasoning_details, reasoning), serializes thinking back as reasoning_content by default, and auto-injects reasoning_effort whenever the conversation history contains prior thinking — so DeepSeek, Qwen, One API and other gateway-fronted services no longer require a hand-set reasoning_key. The reasoning_key model-alias field remains available as an explicit override for non-standard gateways.

  • #66 8ddfc04 - Fix API key input dialog showing a masked dot in empty state.

  • #72 0ce0072 - Fix user skills in ~/.agents/ not being loaded.

  • #86 5e354d0 - Restore real-time token display for running subagents in the TUI.

  • #57 8fb61f9 - Hide the todo panel on resume when all todos are already completed.

  • #83 7d9216d - Always emit a paired tool result when a tool returns a malformed or missing result, preventing the next request from failing with a missing tool_call_id error.

  • #81 1fbefc9 - Improve the Write tool UX.

  • #79 5a90b53 - Fix Plan mode session resets so new sessions no longer fail after plan review rejection and continue receiving events after setup errors.

  • #77 fe60c21 - Exit promptly when the controlling terminal goes away. The TUI now handles SIGHUP / SIGTERM and stdout/stderr EIO / EPIPE / ENOTCONN errors, preventing leftover kimi processes that pin a CPU core after the parent shell or multiplexer dies unexpectedly.

  • #85 2bb50a3 - Avoid overly small local completion caps that can truncate reasoning before summaries are produced.

View original

Upgraded? How did it go?

Discussion