# Kimi Code 0.23.1 - Product: Kimi Code (https://whatsnew.fyi/product/kimi-code) - Vendor: Moonshot AI - Date: 2026-07-07 - Version: 0.23.1 - Original notes: https://github.com/MoonshotAI/kimi-code/releases/tag/%40moonshot-ai/kimi-code%400.23.1 - Permalink: https://whatsnew.fyi/product/kimi-code/releases/0.23.1 - Labels: Platforms: Desktop What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog. Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'. --- - **changed** — Preserve prior turns' thinking by default on the Anthropic provider (Claude and Kimi's Anthropic-compatible mode), matching the Kimi default, with option to disable via `[thinking] keep = "off"` or `KIMI_MODEL_THINKING_KEEP=off` - **fixed** — Recover chat streaming after a stale background-tab WebSocket instead of requiring a page refresh - **fixed** — Fix goal completion and blocked updates to produce one final user-facing outcome summary from the tool result - **fixed** — Fix goal startup and queue handling so failed starts restore permission mode and queued goals wait behind new user messages - **fixed** — Fix goal token budgets to count model completion tokens and stop without extra continuation steps when the budget is exhausted - **fixed** — Fix kimi -p abandoning background subagents that start late or run long, so their results reach the main agent - **fixed** — Respect the --skills-dir flag in interactive mode - **fixed** — Fix `/btw []` opening an empty side chat on the new-session screen - **fixed** — Fix `/goal ` silently doing nothing on the new-session screen - **fixed** — Fix slash skill activations (for example `/pre-changelog`) silently doing nothing on the new-session screen - **changed** — Stop showing tool-produced `` metadata in tool outputs; failed tools now show their own error text - **changed** — Honor explicit Anthropic `max_output_size` settings instead of clamping them to built-in ceilings - **changed** — Keep goal tools available to the main agent and return clear messages for invalid goal-control calls - **fixed** — Fix newer Claude minor versions (e.g. Opus 4.8) defaulting to the family-baseline max output tokens; an uncatalogued minor now reuses the nearest earlier known version's limit - **changed** — Show long-running goal wall-clock budget reminders in hours - **changed** — Tighten goal-mode guidance so agents continue reasonable work across turns instead of ending goals prematurely - **changed** — Clarify the permission mode descriptions shown by `/permission`, `/auto`, and `/yolo`, and reorder `/auto` and `/yolo` in the command list ###### Patch Changes - [#1432](https://github.com/MoonshotAI/kimi-code/pull/1432) [`25a655c`](https://github.com/MoonshotAI/kimi-code/commit/25a655cf88b2f5861f9c0b7ea95ba9308f48d23a) Thanks [@RealKai42](https://github.com/RealKai42)! - Preserve prior turns' thinking by default on the Anthropic provider (Claude and Kimi's Anthropic-compatible mode), matching the Kimi default. Disable with `[thinking] keep = "off"` or `KIMI_MODEL_THINKING_KEEP=off`. - [#1451](https://github.com/MoonshotAI/kimi-code/pull/1451) [`16dc940`](https://github.com/MoonshotAI/kimi-code/commit/16dc940834d9cc693b1f0022c4c70ef0004a6102) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Recover chat streaming after a stale background-tab WebSocket instead of requiring a page refresh. - [#1456](https://github.com/MoonshotAI/kimi-code/pull/1456) [`e9ef939`](https://github.com/MoonshotAI/kimi-code/commit/e9ef9399d075461c7753d1f0467bd742a81cdbf6) Thanks [@chengluyu](https://github.com/chengluyu)! - Fix goal completion and blocked updates to produce one final user-facing outcome summary from the tool result. - [#1456](https://github.com/MoonshotAI/kimi-code/pull/1456) [`e9ef939`](https://github.com/MoonshotAI/kimi-code/commit/e9ef9399d075461c7753d1f0467bd742a81cdbf6) Thanks [@chengluyu](https://github.com/chengluyu)! - Fix goal startup and queue handling so failed starts restore permission mode and queued goals wait behind new user messages. - [#1456](https://github.com/MoonshotAI/kimi-code/pull/1456) [`e9ef939`](https://github.com/MoonshotAI/kimi-code/commit/e9ef9399d075461c7753d1f0467bd742a81cdbf6) Thanks [@chengluyu](https://github.com/chengluyu)! - Fix goal token budgets to count model completion tokens and stop without extra continuation steps when the budget is exhausted. - [#1452](https://github.com/MoonshotAI/kimi-code/pull/1452) [`244ec07`](https://github.com/MoonshotAI/kimi-code/commit/244ec077f98c2b498cee1d0002978b6963ccfd4d) Thanks [@sailist](https://github.com/sailist)! - Fix kimi -p abandoning background subagents that start late or run long, so their results reach the main agent. - [#1457](https://github.com/MoonshotAI/kimi-code/pull/1457) [`260a807`](https://github.com/MoonshotAI/kimi-code/commit/260a80793a95d7796950a00bdc89cf99f8b196ad) Thanks [@liruifengv](https://github.com/liruifengv)! - Respect the --skills-dir flag in interactive mode. - [#1445](https://github.com/MoonshotAI/kimi-code/pull/1445) [`809a88c`](https://github.com/MoonshotAI/kimi-code/commit/809a88cb34d2d5d02e43f030530bb1cd320b4a6a) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Fix `/btw []` opening an empty side chat on the new-session screen. - [#1445](https://github.com/MoonshotAI/kimi-code/pull/1445) [`809a88c`](https://github.com/MoonshotAI/kimi-code/commit/809a88cb34d2d5d02e43f030530bb1cd320b4a6a) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Fix `/goal ` silently doing nothing on the new-session screen. - [#1445](https://github.com/MoonshotAI/kimi-code/pull/1445) [`809a88c`](https://github.com/MoonshotAI/kimi-code/commit/809a88cb34d2d5d02e43f030530bb1cd320b4a6a) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Fix slash skill activations (for example `/pre-changelog`) silently doing nothing on the new-session screen. - [#1437](https://github.com/MoonshotAI/kimi-code/pull/1437) [`743f66e`](https://github.com/MoonshotAI/kimi-code/commit/743f66e547279916d5e37454e78b11eb4b54dca3) Thanks [@RealKai42](https://github.com/RealKai42)! - Stop showing tool-produced `` metadata in tool outputs; failed tools now show their own error text. - [#1465](https://github.com/MoonshotAI/kimi-code/pull/1465) [`bfdbce5`](https://github.com/MoonshotAI/kimi-code/commit/bfdbce593f1dd667530cbfb5b10b5659b1968e48) Thanks [@liruifengv](https://github.com/liruifengv)! - Honor explicit Anthropic `max_output_size` settings instead of clamping them to built-in ceilings. - [#1456](https://github.com/MoonshotAI/kimi-code/pull/1456) [`e _[Truncated at 4000 characters — full notes: https://github.com/MoonshotAI/kimi-code/releases/tag/%40moonshot-ai/kimi-code%400.23.1]_