diff --git a/.changeset/coder-subagent-tool-alignment.md b/.changeset/coder-subagent-tool-alignment.md deleted file mode 100644 index 728e17310..000000000 --- a/.changeset/coder-subagent-tool-alignment.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": minor ---- - -Expand the coder subagent tool set to include background tasks, todo lists, plan mode, skill invocation, and nested agents, mirroring the main agent's capabilities; a subagent run also waits for its background tasks to settle before reporting completion. Applies automatically to coder subagents launched through the Agent tool. diff --git a/.changeset/context-usage-display.md b/.changeset/context-usage-display.md deleted file mode 100644 index 3b13fe7a2..000000000 --- a/.changeset/context-usage-display.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Optimize the unit formatting of the context usage display. diff --git a/.changeset/fix-kimi-provider-effort-fallback.md b/.changeset/fix-kimi-provider-effort-fallback.md deleted file mode 100644 index 9d74e7132..000000000 --- a/.changeset/fix-kimi-provider-effort-fallback.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fix Kimi-provider models routed through the Anthropic protocol incorrectly showing reasoning effort options. Effort choices now come only from the model's declared metadata, and the inferred fallback profile applies solely to non-Kimi Anthropic-compatible providers. diff --git a/.changeset/fix-openai-legacy-thinking-off.md b/.changeset/fix-openai-legacy-thinking-off.md deleted file mode 100644 index 5b46bbf3f..000000000 --- a/.changeset/fix-openai-legacy-thinking-off.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Honor an explicit thinking "off" on OpenAI-compatible (chat completions) providers: it used to be indistinguishable from "never configured", so the history-based auto `reasoning_effort` injection kept the model reasoning (and could leak the field to models that reject it). The provider now also reports the actual current thinking effort ("on"/"off") instead of recording "off" for both. diff --git a/.changeset/fix-web-sidebar-resize-handle.md b/.changeset/fix-web-sidebar-resize-handle.md deleted file mode 100644 index fac669a52..000000000 --- a/.changeset/fix-web-sidebar-resize-handle.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -web: Fix the sidebar resize handle being covered by the chat composer background. diff --git a/.changeset/legacy-migration-targets.md b/.changeset/legacy-migration-targets.md deleted file mode 100644 index e5f765443..000000000 --- a/.changeset/legacy-migration-targets.md +++ /dev/null @@ -1,6 +0,0 @@ ---- -"@moonshot-ai/migration-legacy": patch -"@moonshot-ai/kimi-code": patch ---- - -Keep legacy migrations idempotent across multiple Kimi homes and report damaged or unmapped sessions instead of silently skipping them. diff --git a/.changeset/mid-conversation-switch-warning.md b/.changeset/mid-conversation-switch-warning.md deleted file mode 100644 index 620003eab..000000000 --- a/.changeset/mid-conversation-switch-warning.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Warn in the /model and /effort pickers that switching invalidates the existing prompt cache, and hint to use /new to avoid extra token costs. diff --git a/.changeset/remove-thinking-space-placeholder.md b/.changeset/remove-thinking-space-placeholder.md deleted file mode 100644 index 97acdc099..000000000 --- a/.changeset/remove-thinking-space-placeholder.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Replay empty thinking content verbatim instead of substituting a placeholder space on Anthropic-compatible and Kimi preserved-thinking endpoints. diff --git a/.changeset/report-task-stop-reasons.md b/.changeset/report-task-stop-reasons.md deleted file mode 100644 index 9d6075f4c..000000000 --- a/.changeset/report-task-stop-reasons.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Report when users stop tasks and preserve other stop reasons in model context. diff --git a/.changeset/session-resume-updated-at.md b/.changeset/session-resume-updated-at.md deleted file mode 100644 index dda0464c7..000000000 --- a/.changeset/session-resume-updated-at.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fix a resumed session being marked as just updated and jumping to the top of the session list without any new activity. diff --git a/.changeset/stale-hounds-resume.md b/.changeset/stale-hounds-resume.md deleted file mode 100644 index d66a09463..000000000 --- a/.changeset/stale-hounds-resume.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fix a race where resuming a background subagent right after it was manually stopped could fail with an "already running" error. diff --git a/.changeset/tidy-humans-melt.md b/.changeset/tidy-humans-melt.md deleted file mode 100644 index 76d652b84..000000000 --- a/.changeset/tidy-humans-melt.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fix the context size indicator under-reporting the model's actual context usage. diff --git a/.changeset/vscode-node-sdk-host.md b/.changeset/vscode-node-sdk-host.md deleted file mode 100644 index ab7f3f002..000000000 --- a/.changeset/vscode-node-sdk-host.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -"@moonshot-ai/agent-core": patch -"@moonshot-ai/kimi-code-sdk": patch -"@moonshot-ai/kimi-code": patch ---- - -Support in-process editor hosts with session lifecycle, context, MCP configuration, and cross-platform session storage APIs. diff --git a/.changeset/web-model-picker-full-refresh.md b/.changeset/web-model-picker-full-refresh.md deleted file mode 100644 index dd1e09861..000000000 --- a/.changeset/web-model-picker-full-refresh.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -web: Refresh the model catalog for all providers when opening the model picker, so newly available models always show up. diff --git a/apps/kimi-code/CHANGELOG.md b/apps/kimi-code/CHANGELOG.md index b79709aff..b54a7b4e0 100644 --- a/apps/kimi-code/CHANGELOG.md +++ b/apps/kimi-code/CHANGELOG.md @@ -1,5 +1,39 @@ # @moonshot-ai/kimi-code +## 0.26.0 + +### Minor Changes + +- [#1776](https://github.com/MoonshotAI/kimi-code/pull/1776) [`ffaf0b9`](https://github.com/MoonshotAI/kimi-code/commit/ffaf0b98ca76bb90ba9c989256441dceb468d85f) Thanks [@sailist](https://github.com/sailist)! - Expand the coder subagent tool set to include background tasks, todo lists, plan mode, skill invocation, and nested agents, mirroring the main agent's capabilities; a subagent run also waits for its background tasks to settle before reporting completion. Applies automatically to coder subagents launched through the Agent tool. + +### Patch Changes + +- [#1771](https://github.com/MoonshotAI/kimi-code/pull/1771) [`b513975`](https://github.com/MoonshotAI/kimi-code/commit/b5139757e2df1b5b8723d4bab5137266f5eb0f01) Thanks [@liruifengv](https://github.com/liruifengv)! - Optimize the unit formatting of the context usage display. + +- [#1765](https://github.com/MoonshotAI/kimi-code/pull/1765) [`d531398`](https://github.com/MoonshotAI/kimi-code/commit/d531398d0143cd3b0a2f4a099ff537894c9245e9) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix Kimi-provider models routed through the Anthropic protocol incorrectly showing reasoning effort options. Effort choices now come only from the model's declared metadata, and the inferred fallback profile applies solely to non-Kimi Anthropic-compatible providers. + +- [#1774](https://github.com/MoonshotAI/kimi-code/pull/1774) [`3d5d630`](https://github.com/MoonshotAI/kimi-code/commit/3d5d630c12ea71fb7066e8018dfa2cb6d42da3e8) Thanks [@RealKai42](https://github.com/RealKai42)! - Honor an explicit thinking "off" on OpenAI-compatible (chat completions) providers: it used to be indistinguishable from "never configured", so the history-based auto `reasoning_effort` injection kept the model reasoning (and could leak the field to models that reject it). The provider now also reports the actual current thinking effort ("on"/"off") instead of recording "off" for both. + +- [#1766](https://github.com/MoonshotAI/kimi-code/pull/1766) [`7042af3`](https://github.com/MoonshotAI/kimi-code/commit/7042af3571dbfbf5600535a56692434b84afb4ce) Thanks [@kermanx](https://github.com/kermanx)! - web: Fix the sidebar resize handle being covered by the chat composer background. + +- [#1769](https://github.com/MoonshotAI/kimi-code/pull/1769) [`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Keep legacy migrations idempotent across multiple Kimi homes and report damaged or unmapped sessions instead of silently skipping them. + +- [#1763](https://github.com/MoonshotAI/kimi-code/pull/1763) [`81414b6`](https://github.com/MoonshotAI/kimi-code/commit/81414b6ad5eddb64bbd959a8754ffb6c20b4f6fe) Thanks [@liruifengv](https://github.com/liruifengv)! - Warn in the /model and /effort pickers that switching invalidates the existing prompt cache, and hint to use /new to avoid extra token costs. + +- [#1773](https://github.com/MoonshotAI/kimi-code/pull/1773) [`1169a6d`](https://github.com/MoonshotAI/kimi-code/commit/1169a6d5fdafca4c1455c3ac4889586ef42f4435) Thanks [@RealKai42](https://github.com/RealKai42)! - Replay empty thinking content verbatim instead of substituting a placeholder space on Anthropic-compatible and Kimi preserved-thinking endpoints. + +- [#1781](https://github.com/MoonshotAI/kimi-code/pull/1781) [`09e8554`](https://github.com/MoonshotAI/kimi-code/commit/09e855401be62431b967dcb3b7caf1bcc9705df5) Thanks [@kermanx](https://github.com/kermanx)! - Report when users stop tasks and preserve other stop reasons in model context. + +- [#1784](https://github.com/MoonshotAI/kimi-code/pull/1784) [`d465591`](https://github.com/MoonshotAI/kimi-code/commit/d465591eb3fdb30c0c0348d6edb6f4d3d2f72698) Thanks [@sailist](https://github.com/sailist)! - Fix a resumed session being marked as just updated and jumping to the top of the session list without any new activity. + +- [#1759](https://github.com/MoonshotAI/kimi-code/pull/1759) [`9e3e670`](https://github.com/MoonshotAI/kimi-code/commit/9e3e6700f9276f4ab60219897b297fc96be2355a) Thanks [@sailist](https://github.com/sailist)! - Fix a race where resuming a background subagent right after it was manually stopped could fail with an "already running" error. + +- [#1782](https://github.com/MoonshotAI/kimi-code/pull/1782) [`072eed4`](https://github.com/MoonshotAI/kimi-code/commit/072eed476b5fe7599d994783649a21083320df58) Thanks [@sailist](https://github.com/sailist)! - Fix the context size indicator under-reporting the model's actual context usage. + +- [#1769](https://github.com/MoonshotAI/kimi-code/pull/1769) [`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Support in-process editor hosts with session lifecycle, context, MCP configuration, and cross-platform session storage APIs. + +- [#1772](https://github.com/MoonshotAI/kimi-code/pull/1772) [`78967e2`](https://github.com/MoonshotAI/kimi-code/commit/78967e283d28238337e6437b4824f67b2c3cea7d) Thanks [@sailist](https://github.com/sailist)! - web: Refresh the model catalog for all providers when opening the model picker, so newly available models always show up. + ## 0.25.0 ### Minor Changes diff --git a/apps/kimi-code/package.json b/apps/kimi-code/package.json index 0b51b7cab..7b8a06914 100644 --- a/apps/kimi-code/package.json +++ b/apps/kimi-code/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/kimi-code", - "version": "0.25.0", + "version": "0.26.0", "description": "The Starting Point for Next-Gen Agents", "license": "MIT", "author": "Moonshot AI", diff --git a/packages/agent-core/CHANGELOG.md b/packages/agent-core/CHANGELOG.md index 164f62b3e..9984eb1c3 100644 --- a/packages/agent-core/CHANGELOG.md +++ b/packages/agent-core/CHANGELOG.md @@ -1,5 +1,11 @@ # @moonshot-ai/agent-core +## 0.15.5 + +### Patch Changes + +- [#1769](https://github.com/MoonshotAI/kimi-code/pull/1769) [`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Support in-process editor hosts with session lifecycle, context, MCP configuration, and cross-platform session storage APIs. + ## 0.15.4 ### Patch Changes diff --git a/packages/agent-core/package.json b/packages/agent-core/package.json index 84999b882..d9c1dae09 100644 --- a/packages/agent-core/package.json +++ b/packages/agent-core/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/agent-core", - "version": "0.15.4", + "version": "0.15.5", "private": true, "description": "The unified agent engine for Kimi", "license": "MIT", diff --git a/packages/migration-legacy/CHANGELOG.md b/packages/migration-legacy/CHANGELOG.md index e3bfb31e7..88d4b541f 100644 --- a/packages/migration-legacy/CHANGELOG.md +++ b/packages/migration-legacy/CHANGELOG.md @@ -1,5 +1,14 @@ # @moonshot-ai/migration-legacy +## 0.1.16 + +### Patch Changes + +- [#1769](https://github.com/MoonshotAI/kimi-code/pull/1769) [`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Keep legacy migrations idempotent across multiple Kimi homes and report damaged or unmapped sessions instead of silently skipping them. + +- Updated dependencies [[`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d)]: + - @moonshot-ai/agent-core@0.15.5 + ## 0.1.15 ### Patch Changes diff --git a/packages/migration-legacy/package.json b/packages/migration-legacy/package.json index d68b1d993..52448df87 100644 --- a/packages/migration-legacy/package.json +++ b/packages/migration-legacy/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/migration-legacy", - "version": "0.1.15", + "version": "0.1.16", "description": "Migrate kimi-cli (~/.kimi/) data into kimi-code (~/.kimi-code/).", "license": "MIT", "type": "module", diff --git a/packages/node-sdk/CHANGELOG.md b/packages/node-sdk/CHANGELOG.md index a2bf3356d..4366a54b3 100644 --- a/packages/node-sdk/CHANGELOG.md +++ b/packages/node-sdk/CHANGELOG.md @@ -1,5 +1,11 @@ # @moonshot-ai/kimi-code-sdk +## 0.13.4 + +### Patch Changes + +- [#1769](https://github.com/MoonshotAI/kimi-code/pull/1769) [`d1ca65e`](https://github.com/MoonshotAI/kimi-code/commit/d1ca65e1de189617e9edbc54010e62d472a1de3d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Support in-process editor hosts with session lifecycle, context, MCP configuration, and cross-platform session storage APIs. + ## 0.13.3 ### Patch Changes diff --git a/packages/node-sdk/package.json b/packages/node-sdk/package.json index 7d075720a..961a5462c 100644 --- a/packages/node-sdk/package.json +++ b/packages/node-sdk/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/kimi-code-sdk", - "version": "0.13.3", + "version": "0.13.4", "private": true, "description": "TypeScript SDK for the Kimi Code Agent", "license": "MIT",