MoonshotAI · liruifengv · Aug 18, 2026 · Aug 18, 2026 · Aug 18, 2026 · Aug 18, 2026
diff --git a/.changeset/clean-staged-media.md b/.changeset/clean-staged-media.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Keep pasted image and video attachments available in session history, and clean up temporary uploads automatically.
+Keep pasted image and video attachments available in session history.
diff --git a/.changeset/daemon-file-ref-drop-path.md b/.changeset/daemon-file-ref-drop-path.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code-sdk": minor
 ---
 
-Daemon file references no longer persist a materialization path: the daemon-file URL builder takes only a file id, and the parsed reference no longer carries a `path` field. The display path is derived from the session media store at read time, so a session fork or home relocation can no longer stale a persisted reference. Urls with a legacy `?path=` query still parse.
+Daemon file references no longer persist a materialization path; the display path is derived from the session media store at read time.
diff --git a/.changeset/fix-gemini-thought-signature.md b/.changeset/fix-gemini-thought-signature.md
@@ -1,6 +1,5 @@
 ---
 "@moonshot-ai/kimi-code": patch
-"@moonshot-ai/kimi-code-sdk": patch
 ---
 
-Fix Gemini tool-calling sessions failing on follow-up requests: preserve the tool-call thought signature and keep trailing user text before function results.
+Fix Gemini tool-calling sessions failing on follow-up requests.
diff --git a/.changeset/fix-utf8-text-binary-detection.md b/.changeset/fix-utf8-text-binary-detection.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Fix UTF-8 text files containing Chinese or emoji being misdetected as binary, so log files preview correctly in the web UI.
+Fix text files containing Chinese or emoji being misdetected as binary in the web UI.
diff --git a/.changeset/fork-print-resume-command.md b/.changeset/fork-print-resume-command.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Print the full `kimi --resume` command after `/fork` and copy it to the clipboard, so the fork can be entered directly from a new CLI process.
+Print and copy the full `kimi --resume` command after `/fork`.
diff --git a/.changeset/goal-objective-length-warning.md b/.changeset/goal-objective-length-warning.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Warn in the footer while a typed `/goal` objective exceeds the 4000-character limit, and restore the input instead of losing it when an over-limit objective is rejected. The error message now suggests putting long content in a file and referencing the file path.
+Warn when a typed `/goal` objective exceeds the 4000-character limit, and keep the input if it is rejected.
diff --git a/.changeset/goal-objective-too-long-message.md b/.changeset/goal-objective-too-long-message.md
diff --git a/.changeset/inline-multi-skill-sdk.md b/.changeset/inline-multi-skill-sdk.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code-sdk": minor
 ---
 
-Add `session.promptWithSkills(input, skills)` to submit one prompt with one or more skill activations bundled into the same user message — one turn, one undo unit (v2 engine only; rejects on the v1 engine).
+Add `session.promptWithSkills(input, skills)` to submit one prompt with multiple skill activations in a single turn (v2 engine only).
diff --git a/.changeset/inline-multi-skill-tui.md b/.changeset/inline-multi-skill-tui.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": minor
 ---
 
-Activate multiple skills in a single prompt. Type `/` after whitespace to insert a skill token; all referenced skills run with the prompt as one turn (and undo as one unit).
+Activate multiple skills in a single prompt. Type `/` after whitespace to insert a skill token.
diff --git a/.changeset/inline-slash-trigger-pi-tui.md b/.changeset/inline-slash-trigger-pi-tui.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/pi-tui": patch
 ---
 
-Add an opt-in inline slash autocomplete trigger that fires after whitespace mid-input and at the start of subsequent editor lines.
+Add an opt-in inline slash autocomplete trigger that fires after whitespace mid-input.
diff --git a/.changeset/lazy-global-search-startup.md b/.changeset/lazy-global-search-startup.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Fix several seconds of startup lag: the global search index (used only by the web UI's search) was being opened and synced in every terminal session, including ones that never search. It now loads on demand, so interactive startup stays fast.
+Fix slow startup by loading the global search index on demand.
diff --git a/.changeset/media-registrar-stale-alias.md b/.changeset/media-registrar-stale-alias.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Fix an `[unexpected] Error2: Model "<alias>" is not configured in config.toml` error printed on startup when a restored session references a model that is no longer configured (e.g. after logging out of the managed Kimi Code account). Media tool registration now degrades gracefully instead of throwing from the `agent.status.updated` listener.
+Fix a startup error when a restored session references a model that is no longer configured.
diff --git a/.changeset/persist-token-counting-ledger.md b/.changeset/persist-token-counting-ledger.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Persist the token counting ledger (`token_counting.measured` / `truncated` / `rebased`) to the wire journal, so the displayed context size keeps its measured value after archiving and unarchiving a session (or any close → resume) instead of dropping to a smaller estimate until the next LLM call.
+Fix the displayed context size dropping to a smaller estimate after archiving and resuming a session.
diff --git a/.changeset/queue-skill-commands-while-busy.md b/.changeset/queue-skill-commands-while-busy.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Queue slash skill commands entered while the agent is busy instead of rejecting them with "Cannot /<cmd> while streaming" — they now behave exactly like normal input: queued visibly by default, and Ctrl-S steers them into the running turn as real skill activations.
+Queue slash skill commands entered while the agent is busy instead of rejecting them.
diff --git a/.changeset/sdk-upload-file.md b/.changeset/sdk-upload-file.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code-sdk": minor
 ---
 
-Add `uploadFile` for uploading media to the engine's file store and referencing it from prompts, plus an optional `promptId` on prompt submissions for correlating them with turn-started events. Both require the v2 harness.
+Add `uploadFile` for uploading media and referencing it from prompts, and an optional `promptId` on prompt submissions. Both require the v2 harness.
diff --git a/.changeset/tower-slash-command.md b/.changeset/tower-slash-command.md
diff --git a/.changeset/undo-todo-panel-revert.md b/.changeset/undo-todo-panel-revert.md
@@ -1,6 +1,5 @@
 ---
 "@moonshot-ai/kimi-code": patch
-"@moonshot-ai/kimi-code-sdk": patch
 ---
 
-Fix the todo panel keeping items written by an undone turn: /undo now restores the todo list to its state before the undone turn.
+Fix /undo not restoring the todo list to its state before the undone turn.
diff --git a/.changeset/v1-mcp-management-plane-sdk.md b/.changeset/v1-mcp-management-plane-sdk.md
@@ -0,0 +1,5 @@
+---
+"@moonshot-ai/kimi-code-sdk": minor
+---
+
+Unify the MCP management surface behind a source-tagged registry, covering plugin-declared servers in `listMcpServers` and adding `getMcpServer`, `testMcpServerConfig`, runtime `addMcpServer`, `inspectAppMcpServers`, and an `oauth-expired` auth state.
diff --git a/.changeset/v1-mcp-management-plane-vscode.md b/.changeset/v1-mcp-management-plane-vscode.md
@@ -0,0 +1,5 @@
+---
+"kimi-code": patch
+---
+
+Show plugin- and file-declared MCP servers as read-only entries in the MCP servers panel.
diff --git a/.changeset/v1-mcp-management-plane.md b/.changeset/v1-mcp-management-plane.md
@@ -1,9 +1,5 @@
 ---
 "@moonshot-ai/kimi-code": patch
-"@moonshot-ai/kimi-code-sdk": minor
-"kimi-code": patch
 ---
 
-On the legacy engine, plugin MCP server changes (install / enable / disable / remove / reload) now apply to open sessions immediately, and an MCP server OAuth sign-in or credential reset automatically refreshes the affected sessions instead of leaving them stuck until a manual reconnect; a connection that fails mid-session for auth reasons is now reported as needing sign-in rather than as a generic failure.
-
-`@moonshot-ai/kimi-code-sdk`: the MCP management surface is now backed by a unified, source-tagged registry — `listMcpServers` also covers plugin-declared servers (read-only, with their effective config) and returns `source` / `origin` / `mutable` markers; new `getMcpServer` for a single effective config; `testMcpServerConfig` probes an unsaved inline config; sessions can connect a server at runtime via `addMcpServer` with an optional persist flag; `reconnectMcpServer` accepts an optional replacement config and otherwise re-resolves the current config instead of reusing a stale snapshot; `listMcpServerAuthStatuses` accepts `cwd` / `verify` (online probe) and distinguishes dead grants via the new `oauth-expired` state; stored OAuth grants now record their absolute expiry and are refreshed proactively and single-flight per credential. Session status entries and read-only management entries redact secret-bearing stdio `env` / remote `headers` values to key lists, and concurrent logins for the same credential join a single browser flow. A new app-level inspection, `inspectAppMcpServers`, reports every server's effective config and real (probe-verified) authorization state — including plugin servers and runtime-name collisions — and the OAuth flow RPCs have locator-addressed variants (`authenticateAppMcpServer` / `resetAppMcpServerAuth`) so plugin servers can be signed in and reset directly.
+On the legacy engine, plugin MCP server changes and OAuth sign-in now take effect in open sessions immediately.
diff --git a/.changeset/web-title-flag.md b/.changeset/web-title-flag.md
@@ -2,4 +2,4 @@
 "@moonshot-ai/kimi-code": patch
 ---
 
-Add `kimi web --web-title <title>` to set a custom browser tab title for the web UI instance, so multiple instances on different machines are easy to tell apart; without the flag the tab title shows the active workspace's directory name.
+Add `kimi web --web-title <title>` to set a custom browser tab title for the web UI.