packages/node-sdk/CHANGELOG.md

@moonshot-ai/kimi-code-sdk

0.20.0

Minor Changes

• #3453 411572e Thanks @Grapedge! - Add suggestFiles(workDir, { query, limit }) to KimiHarness: session-less fuzzy file suggestions from the agent-core-v2 workspace fs service, undefined on the v1 engine.

0.19.2

Patch Changes

• #3098 75550c5 Thanks @LCZcn96! - Restore live context-window usage updates after switching to the v2 engine.

• #3002 d723cc4 Thanks @7Sageer! - Add an optional cwd parameter to the global MCP management methods; verify: false on the global MCP authorization-status listing now returns a fully offline classification instead of behaving like an omitted verify.

0.19.1

Patch Changes

• #2862 3d77620 Thanks @liruifengv! - Add an optional region parameter to the auth login API for selecting the OAuth login endpoint (.com or .ai deployment).

0.19.0

Minor Changes

• #2593 d833a1a Thanks @7Sageer! - Daemon file references no longer persist a materialization path; the display path is derived from the session media store at read time.

• #2934 61591bc Thanks @chengluyu! - Add session.promptWithSkills(input, skills) to submit one prompt with multiple skill activations in a single turn (v2 engine only).

• #2593 d833a1a Thanks @7Sageer! - Add uploadFile for uploading media and referencing it from prompts, and an optional promptId on prompt submissions. Both require the v2 harness.

• #3026 13857f3 Thanks @bj456736! - 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.

0.18.0

Minor Changes

• #2351 6be2697 Thanks @7Sageer! - Add generateSessionTitle (v2 engine) for managed AI session titles: optional force regeneration over generated/custom titles and selectable conversation excerpts (user_prompts / first_turn / digest). Gated by the experimental auto_session_title flag and a managed OAuth login.

Patch Changes

• #2916 7475c2e Thanks @Grapedge! - Cascade turn cancellation to the session-level /init run in the v2-backed client.

• #2916 7475c2e Thanks @Grapedge! - Implement session deletion in the v2-backed client.

• #2916 7475c2e Thanks @Grapedge! - Support forking a session from a specific turn in the v2-backed client, and reject forking a live session while its turn is running.

0.17.0

Minor Changes

• #2700 c9bfe8b Thanks @7Sageer! - Remove the secondary-model session API Session.applyPersistedSecondaryModel; subagent model selection is configured via [secondary_model] in config.toml instead. The SECONDARY_DERIVED_MODEL_ALIAS export stays (the v1 engine still synthesizes the entry at runtime, so hosts keep filtering it out of model pickers), and the SDK now also exports PRIMARY_SUBAGENT_MODEL_CHOICE, the v2 subagent model pool's reserved primary key.

Patch Changes

• #2843 c212ae9 Thanks @sailist! - Show project MCP launch targets in the workspace trust prompt, default to declining trust, and resolve fd and stty binaries to absolute paths so untrusted workspaces cannot plant bare-name executables before confirmation.

  @moonshot-ai/kimi-code-sdk contract change: WorkspaceTrustInfo.gatedMcpServers now carries structured WorkspaceTrustMcpServerInfo records (name, transport, and command/args/cwd or url) instead of plain strings, so SDK consumers rendering a trust prompt can show the full launch target.

0.16.0

Minor Changes

• #2826 3c9e3b2 Thanks @liruifengv! - Add listSessionsPage for keyset-paged session listing (limit / before, returns nextCursor). The v2 engine pages through the session index; the v1 engine keeps answering with a single full page.

Patch Changes

• #2731 437a1b8 Thanks @pvzheroes125! - Detect MCP servers that require OAuth without needing auth: "oauth" in the config.

• #2706 0b2e803 Thanks @pvzheroes125! - Expose persisted MCP authorization status without starting an OAuth flow.

0.15.3

Patch Changes

• #2666 335588e Thanks @wbxl2000! - Session listings keep how the last turn ended (completed, cancelled, or failed) across server restarts, so clients can mark previously failed sessions before they are opened.

• #2679 7b2784b Thanks @liruifengv! - Subagent lifecycle events and background task info now carry the subagent's bound model and thinking effort.

0.15.2

Patch Changes

• #2601 75fe068 Thanks @wbxl2000! - Fix built-in capability availability and installed status in /plugins, preserve legacy WebBridge skills as backups during updates, and prevent Computer Use updates from duplicating or disconnecting MCP servers.

0.15.1

Patch Changes

• #2567 98ef0f0 Thanks @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

• #2382 40172c7 Thanks @liruifengv! - Rename userAgentProduct to productName and require platform in the host identity options exposed by the SDK.

0.14.0

Minor Changes

• #1735 ce0e3ce Thanks @7Sageer! - Add global tool gating to constrain which tools agents may use, with a per-session override (v2 engine only).

Patch Changes

• #2030 ec88d35 Thanks @RealKai42! - Fix catalog-imported Claude models being wrongly locked into always-on thinking, and stop offering a misleading thinking Off option for models that cannot truly disable reasoning (such as Gemini 3). Also normalizes configured thinking effort values and unifies context-usage reporting.

• #2015 b5efba7 Thanks @RealKai42! - Import many more providers from the models.dev catalog: vendor SDKs like xai and openrouter now import instead of being refused (with a "guessed" note), deprecated and alpha models are filtered out, per-model gateway protocol and endpoint overrides are honored, and context limits are correct (input limit for compaction, total window for completion). Imports lacking a usable endpoint now ask for one via --base-url or a prompt.

• #1976 e458323 Thanks @liruifengv! - Improve TUI performance and resume speed for long-running sessions.

0.13.4

Patch Changes

• #1769 d1ca65e Thanks @wbxl2000! - Support in-process editor hosts with session lifecycle, context, MCP configuration, and cross-platform session storage APIs.

0.13.3

Patch Changes

• #1488 7bd29ab Thanks @starquakee! - Rename the dynamic tool loading model capability from select_tools to dynamically_loaded_tools.

0.13.2

Patch Changes

• #1501 b91099e Thanks @liruifengv! - Display Extra Usage (fuel pack) balance in /usage and /status commands.

0.13.1

Patch Changes

• #1460 474ce28 Thanks @RealKai42! - Raise the image downscale cap from 2000px to 3000px, and fix swapped width/height for EXIF-rotated (portrait) photos in compression captions and media read notes so region readback coordinates map correctly.

0.13.0

Minor Changes

• #1369 f0896a5 Thanks @starquakee! - Add experimental progressive tool disclosure (select_tools). When the tool-select experimental flag is on and the active model declares the select_tools capability, MCP tool schemas stay out of the request's top-level tools[] (preserving the provider prompt cache); the model loads tools on demand by exact name via the new built-in select_tools tool, guided by <tools_added>/<tools_removed> announcements. Off by default and inert on models without the capability — behavior is unchanged until a supporting model is catalogued. The SDK additionally maps the select_tools capability when building model aliases from a catalog and reports the new flag through getExperimentalFeatures().

0.12.1

Patch Changes

• #1349 e9db9ca - Record model response ids in session wire logs to make individual model requests easier to trace.

0.12.0

Minor Changes

• #1243 ace7901 - Automatically compress oversized images before they reach the model. Whatever the source — pasted into the CLI, uploaded from the web/desktop client, sent over ACP, read via ReadMediaFile, or returned by an MCP tool — images are downsampled (longest edge ≤ 2000px) and re-encoded to fit a per-image byte budget, cutting vision-token cost and avoiding provider image-size errors. Screenshots stay lossless PNG and only degrade to JPEG when the byte budget cannot otherwise be met. Compression runs as an input-stage step at each ingestion point (while the content part is built), and guards against decompression bombs by skipping absurdly large pixel/byte payloads before decoding. Best-effort: if it fails for any reason the original image is sent unchanged.

0.11.0

Minor Changes

• #1132 108299b - Refactor the thinking effort system

0.10.1

Patch Changes

• #1120 e736349 - Add optional feedback attachments for diagnostic logs and codebase context.

0.10.0

Minor Changes

• #812 c0eeca2 - Added the ability to add extra workspace directories:

  • Use the /add-dir <path> command to add extra working directories to the current session, or remember them for the project.
  • Use kimi --add-dir <path> to add them on startup.
  • Project-level local config is now managed in .kimi-code/local.toml; we recommend adding it to your .gitignore.

Patch Changes

• #821 ba64072 - Allow long-running foreground commands and subagents to be moved into background tasks with Ctrl+B, and inspect them via the /tasks panel.

0.9.4

Patch Changes

• #838 843a731 - Show the underlying connection error when OAuth token refresh fails after internal retries, instead of prompting for login. Token refresh failures are no longer re-retried at the agent loop level.

• #625 9a8fea5 - Add host-side config helpers loadRuntimeConfigSafe and resolveConfigPath for inspecting config without spinning up a full KimiCore.

0.9.3

Patch Changes

• #689 8d251f8 - Drop invalid config.toml sections with a warning instead of failing to start.

0.9.2

Patch Changes

• #648 54302ad - Prevent overlapping interactive agent requests from using the wrong active agent.

0.9.1

Patch Changes

• #591 e48234a - Fix Windows builds and development launches that could fail when package binaries resolve to command shims.

0.9.0

Minor Changes

• #487 4d11394 - Honor the standard HTTP_PROXY / HTTPS_PROXY / ALL_PROXY / NO_PROXY environment variables, including SOCKS proxies, for all outbound traffic.

• #424 72c4b0a - Add the /swarm command for running agent swarms with live progress and rate-limit-aware retries.

Patch Changes

• #395 879a7ee - Fix ACP slash skill routing, bootstrap context reads, file and permission edge cases, subagent event handling, and stale-file edit messaging.

• #552 db82e33 - Fix goal resume behavior by restoring goal state from agent records.

0.8.0

Minor Changes

• #420 86a42a2 - Add persistent experimental feature toggles and a TUI panel that applies confirmed changes by reloading the current session.

• #383 15d71b5 - Add /reload to reload the current session and apply updated config files, plus /reload-tui to reload only TUI preferences.

• #431 6a4e4c7 - Add a doctor command for validating Kimi Code configuration files.

Patch Changes

• #399 232ed87 - Keep managed OAuth credentials scoped to their configured authentication and API endpoints.

• #430 be0da5f - Fail early when Git Bash is missing on Windows before starting CLI sessions.

0.7.0

Minor Changes

• #338 ba7dd73 - Add /btw for side-channel conversations without steering the active main turn.

• #339 a6b16ce - Allow SDK runtime creation to use a separate RPC client while preserving local CLI startup.

0.6.0

Minor Changes

• #270 ac37d74 - Add experimental goal mode for longer tasks that need more than one turn. Turn it on with KIMI_CODE_EXPERIMENTAL_GOAL_COMMAND=1 before you start Kimi.

  Use /goal <objective> in the TUI when you want Kimi to keep working on one task across turns. For example:

  /goal Fix the failing checkout test
  

  Kimi shows the goal in the TUI and keeps progress visible while it works. Use /goal status, /goal pause, /goal resume, /goal cancel, and /goal replace <objective> to manage the goal. This feature is still experimental. Try it and tell us what would make it more useful.

• #315 191059d - Add background structured questions so agents can continue while waiting for user answers.

Patch Changes

• #145 d912053 - Fix Git Bash path detection on Windows by also searching usr\bin\bash.exe locations, which is where bash lives in many Git for Windows installations where bin\bash.exe does not exist.

0.5.0

Minor Changes

• #204 ee69d0a - Render scheduled reminders distinctly in the TUI, expose cron fired events to SDK clients, and report cron fire times with local timezone offsets.

0.4.0

Minor Changes

• #221 bab2da7 - Install plugins directly from GitHub repository URLs, and surface each install's origin and trust level (kimi-official, curated, third-party) in the plugin manager.

• #118 8913440 - Support querying sessions by sessionId or workDir in listSessions, and show a helpful cd command when resuming a session from a different working directory.

Patch Changes

• #221 bab2da7 - Restrict plugin trust badges to Kimi-hosted plugin CDN URL patterns.

0.3.0

Minor Changes

• #119 ebf6e81 - Add user-global plugin installation, interactive plugin management, plugin-provided skills, and plugin-owned MCP servers.

• #113 028d069 - Add /export-md slash command to export the current session as a Markdown file.

Patch Changes

• #105 d599183 - Enhance kimi export to include more diagnostic information in the manifest.

0.2.1

Patch Changes

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

0.2.0

Minor Changes

• #30 a200a29 - Add a /connect command that configures a provider and model from a model catalog.

Patch Changes

• #33 ab4bd09 - Report the macOS product version in OAuth device information instead of the Darwin kernel version.

• #49 cf2227e - Resume sessions with a newer wire protocol version instead of failing. A warning is now shown in the TUI and records are replayed without migration.