diff --git a/.changeset/catalog-builtin-fallback.md b/.changeset/catalog-builtin-fallback.md deleted file mode 100644 index 712144ec88..0000000000 --- a/.changeset/catalog-builtin-fallback.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fall back to the built-in models.dev catalog snapshot when the public catalog is unreachable, so Known third-party provider import still works offline or in blocked networks. diff --git a/.changeset/fix-dark-mono-composer.md b/.changeset/fix-dark-mono-composer.md deleted file mode 100644 index 929ca229c9..0000000000 --- a/.changeset/fix-dark-mono-composer.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -web: Fix dark-mode monochrome controls and align the chat composer corner radius with the design system. diff --git a/.changeset/hook-events-lifecycle-coverage.md b/.changeset/hook-events-lifecycle-coverage.md deleted file mode 100644 index 0ba5e2aa21..0000000000 --- a/.changeset/hook-events-lifecycle-coverage.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": minor ---- - -Add the TurnStarted, UserPromptQueued, TaskStarted, and SessionHeartbeat hook events, enrich hook payloads with the session title and client type, include the model and profile in SessionStart, and report SessionEnd as archive when a session is archived instead of exited. Configure the new events under [[hooks]] in config.toml. diff --git a/.changeset/kap-server-config-warning-event.md b/.changeset/kap-server-config-warning-event.md deleted file mode 100644 index 7312d1e3e2..0000000000 --- a/.changeset/kap-server-config-warning-event.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kap-server": patch ---- - -Add the global `event.config.warning` WebSocket event that pushes the current set of config warnings (deprecated config keys or environment variables in use) to every connection whenever it changes. diff --git a/.changeset/kap-server-meta-experimental-flags.md b/.changeset/kap-server-meta-experimental-flags.md deleted file mode 100644 index ac946e9449..0000000000 --- a/.changeset/kap-server-meta-experimental-flags.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kap-server": patch ---- - -Expose the effective experimental-flag map as `experimental_flags` on `GET /api/v1/meta`. diff --git a/.changeset/login-already-logged-in-visibility.md b/.changeset/login-already-logged-in-visibility.md deleted file mode 100755 index 265ebed5ac..0000000000 --- a/.changeset/login-already-logged-in-visibility.md +++ /dev/null @@ -1,4 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- -Render the "/login" already-logged-in confirmation in the success color instead of dim text, so the "Already logged in. Model configuration refreshed." message is clearly visible. diff --git a/.changeset/loop-control-attempt-limit-rename.md b/.changeset/loop-control-attempt-limit-rename.md deleted file mode 100644 index 2f81943bba..0000000000 --- a/.changeset/loop-control-attempt-limit-rename.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Rename the `[loop_control] max_retries_per_step` config key to `max_attempts_per_step` and `max_steps_per_run` to `max_steps_per_turn`: on the v2 engine the old keys no longer take effect and a startup warning prompts the rename in `config.toml`. The `KIMI_LOOP_MAX_RETRIES_PER_STEP` env var is likewise deprecated in favor of `KIMI_LOOP_MAX_ATTEMPTS_PER_STEP` but keeps working with a warning. diff --git a/.changeset/questions-colon-id-resolve.md b/.changeset/questions-colon-id-resolve.md deleted file mode 100644 index 6404aacb9f..0000000000 --- a/.changeset/questions-colon-id-resolve.md +++ /dev/null @@ -1,6 +0,0 @@ ---- -"@moonshot-ai/kap-server": patch -"@moonshot-ai/kimi-code": patch ---- - -Fix submitting answers to interactive question prompts being rejected when the model provider returns tool call IDs containing colons (some OpenAI-compatible gateways). diff --git a/.changeset/server-owns-v1-message-history.md b/.changeset/server-owns-v1-message-history.md deleted file mode 100644 index aafd69b17b..0000000000 --- a/.changeset/server-owns-v1-message-history.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -"@moonshot-ai/agent-core-v2": patch -"@moonshot-ai/kap-server": patch -"@moonshot-ai/kimi-code": patch ---- - -Serve v1 message history from the server layer and drop the engine-side legacy message adapter; the /api/v1 message contract is unchanged. diff --git a/.changeset/snapshot-via-engine-services.md b/.changeset/snapshot-via-engine-services.md deleted file mode 100644 index 86284a2c1b..0000000000 --- a/.changeset/snapshot-via-engine-services.md +++ /dev/null @@ -1,6 +0,0 @@ ---- -"@moonshot-ai/kap-server": patch -"@moonshot-ai/kimi-code": patch ---- - -Assemble the session snapshot endpoint from the engine's services for both cold and live sessions, and remove the KIMI_SNAPSHOT_READER, KIMI_SNAPSHOT_TIMEOUT_MS, and KIMI_SNAPSHOT_CACHE_LIMIT environment knobs. diff --git a/.changeset/tidy-llamas-attend.md b/.changeset/tidy-llamas-attend.md deleted file mode 100644 index aa24afe646..0000000000 --- a/.changeset/tidy-llamas-attend.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Fix the context window limit showing as 0 in session status updates when no model is bound yet or the configured model no longer resolves; the limit now falls back to the default model or is omitted when unknown. diff --git a/.changeset/token-counting-reporting-edge.md b/.changeset/token-counting-reporting-edge.md deleted file mode 100644 index f5345b172f..0000000000 --- a/.changeset/token-counting-reporting-edge.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -The `[token_counting]` strategy now only selects the reported context size: `estimated` keeps provider-reported usage out of the context-size display, and `measured` no longer gets stuck retrying an oversized compaction request until it fails. diff --git a/.changeset/token-counting-strategy.md b/.changeset/token-counting-strategy.md deleted file mode 100644 index 53415ee46a..0000000000 --- a/.changeset/token-counting-strategy.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code": patch ---- - -Add a `[token_counting]` config section to choose how context token counts are derived: `measured+estimated` (default), `measured` (provider usage only), or `estimated` (heuristic only, for providers without usage reporting). Set `strategy` under `[token_counting]` in config.toml (or `KIMI_TOKEN_COUNTING_STRATEGY`) to switch. diff --git a/.changeset/v1-replay-profile-bind.md b/.changeset/v1-replay-profile-bind.md deleted file mode 100644 index 2818e4f0b1..0000000000 --- a/.changeset/v1-replay-profile-bind.md +++ /dev/null @@ -1,5 +0,0 @@ ---- -"@moonshot-ai/kimi-code-sdk": patch ---- - -Fix v1 replay ignoring v2 `profile.bind` records, which made sessions resumed from CLI-created wires lose their tool allowlist and send requests without `tools`. diff --git a/apps/kimi-code/CHANGELOG.md b/apps/kimi-code/CHANGELOG.md index 479eefd700..3ccd65f0cb 100644 --- a/apps/kimi-code/CHANGELOG.md +++ b/apps/kimi-code/CHANGELOG.md @@ -1,5 +1,33 @@ # @moonshot-ai/kimi-code +## 0.32.0 + +### Minor Changes + +- [#2558](https://github.com/MoonshotAI/kimi-code/pull/2558) [`75395f6`](https://github.com/MoonshotAI/kimi-code/commit/75395f6abb17f83f30d16b51f4e060a639f43622) Thanks [@sailist](https://github.com/sailist)! - Add the TurnStarted, UserPromptQueued, TaskStarted, and SessionHeartbeat hook events, enrich hook payloads with the session title and client type, include the model and profile in SessionStart, and report SessionEnd as archive when a session is archived instead of exited. Configure the new events under [[hooks]] in config.toml. + +### Patch Changes + +- [#2416](https://github.com/MoonshotAI/kimi-code/pull/2416) [`eaab2b6`](https://github.com/MoonshotAI/kimi-code/commit/eaab2b6f28c0b958edf8ab5ae5e78a4c0426af26) Thanks [@mangeshraut712](https://github.com/mangeshraut712)! - Fall back to the built-in models.dev catalog snapshot when the public catalog is unreachable, so Known third-party provider import still works offline or in blocked networks. + +- [#2083](https://github.com/MoonshotAI/kimi-code/pull/2083) [`bfa0080`](https://github.com/MoonshotAI/kimi-code/commit/bfa00807c975fdc5b84dda32d47b16b09e8d42c1) Thanks [@StaR4y](https://github.com/StaR4y)! - web: Fix dark-mode monochrome controls and align the chat composer corner radius with the design system. + +- [#2559](https://github.com/MoonshotAI/kimi-code/pull/2559) [`dfc55a5`](https://github.com/MoonshotAI/kimi-code/commit/dfc55a5c977dbff657e1da74ff5c2b9d488807be) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Render the "/login" already-logged-in confirmation in the success color instead of dim text, so the "Already logged in. Model configuration refreshed." message is clearly visible. + +- [#2572](https://github.com/MoonshotAI/kimi-code/pull/2572) [`6ba75a1`](https://github.com/MoonshotAI/kimi-code/commit/6ba75a173b595904bc70d0d7161de2f9b964c961) Thanks [@sailist](https://github.com/sailist)! - Rename the `[loop_control] max_retries_per_step` config key to `max_attempts_per_step` and `max_steps_per_run` to `max_steps_per_turn`: on the v2 engine the old keys no longer take effect and a startup warning prompts the rename in `config.toml`. The `KIMI_LOOP_MAX_RETRIES_PER_STEP` env var is likewise deprecated in favor of `KIMI_LOOP_MAX_ATTEMPTS_PER_STEP` but keeps working with a warning. + +- [#2585](https://github.com/MoonshotAI/kimi-code/pull/2585) [`c396873`](https://github.com/MoonshotAI/kimi-code/commit/c39687318c64bf8a305a10bf9ca86ef6ef2c6656) Thanks [@sailist](https://github.com/sailist)! - Fix submitting answers to interactive question prompts being rejected when the model provider returns tool call IDs containing colons (some OpenAI-compatible gateways). + +- [#2562](https://github.com/MoonshotAI/kimi-code/pull/2562) [`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52) Thanks [@sailist](https://github.com/sailist)! - Serve v1 message history from the server layer and drop the engine-side legacy message adapter; the /api/v1 message contract is unchanged. + +- [#2562](https://github.com/MoonshotAI/kimi-code/pull/2562) [`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52) Thanks [@sailist](https://github.com/sailist)! - Assemble the session snapshot endpoint from the engine's services for both cold and live sessions, and remove the KIMI_SNAPSHOT_READER, KIMI_SNAPSHOT_TIMEOUT_MS, and KIMI_SNAPSHOT_CACHE_LIMIT environment knobs. + +- [#2563](https://github.com/MoonshotAI/kimi-code/pull/2563) [`2118544`](https://github.com/MoonshotAI/kimi-code/commit/21185447fe0f04dbe342bebb6c6d0b364fd43daa) Thanks [@sailist](https://github.com/sailist)! - Fix the context window limit showing as 0 in session status updates when no model is bound yet or the configured model no longer resolves; the limit now falls back to the default model or is omitted when unknown. + +- [#2563](https://github.com/MoonshotAI/kimi-code/pull/2563) [`2118544`](https://github.com/MoonshotAI/kimi-code/commit/21185447fe0f04dbe342bebb6c6d0b364fd43daa) Thanks [@sailist](https://github.com/sailist)! - The `[token_counting]` strategy now only selects the reported context size: `estimated` keeps provider-reported usage out of the context-size display, and `measured` no longer gets stuck retrying an oversized compaction request until it fails. + +- [#2563](https://github.com/MoonshotAI/kimi-code/pull/2563) [`2118544`](https://github.com/MoonshotAI/kimi-code/commit/21185447fe0f04dbe342bebb6c6d0b364fd43daa) Thanks [@sailist](https://github.com/sailist)! - Add a `[token_counting]` config section to choose how context token counts are derived: `measured+estimated` (default), `measured` (provider usage only), or `estimated` (heuristic only, for providers without usage reporting). Set `strategy` under `[token_counting]` in config.toml (or `KIMI_TOKEN_COUNTING_STRATEGY`) to switch. + ## 0.31.1 ### Patch Changes diff --git a/apps/kimi-code/package.json b/apps/kimi-code/package.json index cb617c8046..ea52280f2a 100644 --- a/apps/kimi-code/package.json +++ b/apps/kimi-code/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/kimi-code", - "version": "0.31.1", + "version": "0.32.0", "description": "The Starting Point for Next-Gen Agents", "license": "MIT", "author": "Moonshot AI", diff --git a/packages/agent-core-v2/CHANGELOG.md b/packages/agent-core-v2/CHANGELOG.md index a4cbfaaaaa..94e48650da 100644 --- a/packages/agent-core-v2/CHANGELOG.md +++ b/packages/agent-core-v2/CHANGELOG.md @@ -1,5 +1,11 @@ # @moonshot-ai/agent-core-v2 +## 0.3.1 + +### Patch Changes + +- [#2562](https://github.com/MoonshotAI/kimi-code/pull/2562) [`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52) Thanks [@sailist](https://github.com/sailist)! - Serve v1 message history from the server layer and drop the engine-side legacy message adapter; the /api/v1 message contract is unchanged. + ## 0.3.0 ### Minor Changes diff --git a/packages/agent-core-v2/package.json b/packages/agent-core-v2/package.json index 00082474cd..03fcea8bfe 100644 --- a/packages/agent-core-v2/package.json +++ b/packages/agent-core-v2/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/agent-core-v2", - "version": "0.3.0", + "version": "0.3.1", "private": true, "description": "The unified agent engine for Kimi (v2 — DI Scope architecture)", "license": "MIT", diff --git a/packages/kap-server/CHANGELOG.md b/packages/kap-server/CHANGELOG.md index f9378d92a8..d81d2b1432 100644 --- a/packages/kap-server/CHANGELOG.md +++ b/packages/kap-server/CHANGELOG.md @@ -1,5 +1,22 @@ # @moonshot-ai/kap-server +## 0.2.1 + +### Patch Changes + +- [#2572](https://github.com/MoonshotAI/kimi-code/pull/2572) [`6ba75a1`](https://github.com/MoonshotAI/kimi-code/commit/6ba75a173b595904bc70d0d7161de2f9b964c961) Thanks [@sailist](https://github.com/sailist)! - Add the global `event.config.warning` WebSocket event that pushes the current set of config warnings (deprecated config keys or environment variables in use) to every connection whenever it changes. + +- [#2417](https://github.com/MoonshotAI/kimi-code/pull/2417) [`e22479a`](https://github.com/MoonshotAI/kimi-code/commit/e22479a62eed9c3b78a67b313f4332c2c0ba9670) Thanks [@liruifengv](https://github.com/liruifengv)! - Expose the effective experimental-flag map as `experimental_flags` on `GET /api/v1/meta`. + +- [#2585](https://github.com/MoonshotAI/kimi-code/pull/2585) [`c396873`](https://github.com/MoonshotAI/kimi-code/commit/c39687318c64bf8a305a10bf9ca86ef6ef2c6656) Thanks [@sailist](https://github.com/sailist)! - Fix submitting answers to interactive question prompts being rejected when the model provider returns tool call IDs containing colons (some OpenAI-compatible gateways). + +- [#2562](https://github.com/MoonshotAI/kimi-code/pull/2562) [`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52) Thanks [@sailist](https://github.com/sailist)! - Serve v1 message history from the server layer and drop the engine-side legacy message adapter; the /api/v1 message contract is unchanged. + +- [#2562](https://github.com/MoonshotAI/kimi-code/pull/2562) [`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52) Thanks [@sailist](https://github.com/sailist)! - Assemble the session snapshot endpoint from the engine's services for both cold and live sessions, and remove the KIMI_SNAPSHOT_READER, KIMI_SNAPSHOT_TIMEOUT_MS, and KIMI_SNAPSHOT_CACHE_LIMIT environment knobs. + +- Updated dependencies [[`071b6a5`](https://github.com/MoonshotAI/kimi-code/commit/071b6a50d9c2ce9c4b45dc4d58dac1101b8c4f52)]: + - @moonshot-ai/agent-core-v2@0.3.1 + ## 0.2.0 ### Minor Changes diff --git a/packages/kap-server/package.json b/packages/kap-server/package.json index 937f366df5..e2b869539b 100644 --- a/packages/kap-server/package.json +++ b/packages/kap-server/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/kap-server", - "version": "0.2.0", + "version": "0.2.1", "private": true, "description": "Kimi Code server backed by the DI × Scope agent engine (agent-core-v2)", "type": "module", diff --git a/packages/node-sdk/CHANGELOG.md b/packages/node-sdk/CHANGELOG.md index ddd2edf6a7..2b397f448d 100644 --- a/packages/node-sdk/CHANGELOG.md +++ b/packages/node-sdk/CHANGELOG.md @@ -1,5 +1,11 @@ # @moonshot-ai/kimi-code-sdk +## 0.15.1 + +### Patch Changes + +- [#2567](https://github.com/MoonshotAI/kimi-code/pull/2567) [`98ef0f0`](https://github.com/MoonshotAI/kimi-code/commit/98ef0f0b2ffaef84903b9c116ada0eeb4c8e9a6c) Thanks [@7Sageer](https://github.com/7Sageer)! - Fix v1 replay ignoring v2 `profile.bind` records, which made sessions resumed from CLI-created wires lose their tool allowlist and send requests without `tools`. + ## 0.15.0 ### Minor Changes diff --git a/packages/node-sdk/package.json b/packages/node-sdk/package.json index 17c3bf11ed..96428344f3 100644 --- a/packages/node-sdk/package.json +++ b/packages/node-sdk/package.json @@ -1,6 +1,6 @@ { "name": "@moonshot-ai/kimi-code-sdk", - "version": "0.15.0", + "version": "0.15.1", "private": true, "description": "TypeScript SDK for the Kimi Code Agent", "license": "MIT",