- unconditionally expose /openapi.json and /asyncapi.json\n- add --swagger flag to kimi server run\n- mount Swagger UI at /documentation only when --swagger is passed\n- generate AsyncAPI document from ws-control schemas\n- update tests and docs
* feat(skill): qualify sub-skill names with parent prefix
- qualify sub-skill names with parent prefix and set isSubSkill metadata\n- hide sub-skills from the model skill listing
- expose sub-skills as dotted slash commands in TUI
- update slash command docs for English and Chinese
- align built-in sub-skill local names with their directories
- rename workspace package `@moonshot-ai/daemon` to `@moonshot-ai/server`\n- rename `@moonshot-ai/daemon-e2e` to `@moonshot-ai/server-e2e`\n- replace `kimi daemon` and `kimi web` with `kimi server run`\n- keep `kimi web` as alias for `kimi server run --open`\n- add `kimi server install/uninstall/start/stop/restart/status`\n for launchd (darwin), systemd (linux), and schtasks (win32)\n- update dev scripts, kimi-web stub, documentation, and service naming checks\n\nBREAKING CHANGE: the `kimi daemon` command and `@moonshot-ai/daemon`\npackage are removed; use `kimi server` and `@moonshot-ai/server`.
* fix: clean up background tasks on session exit
* Stop background tasks on session close
Change versioning for agent-core and kimi-code to patch.
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
---------
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
- ThinkingBlock: foldable last-paragraph teaser, hover-only indicator,
auto-collapse when streaming ends, line-height aligned with content
- ChatPane: static turn-summary at end of assistant turns
- Composer: perm-pill background matches toggle-pill
- SessionRow: kebab button moved before timestamp
- ToolCall: replace text chevron with SVG
- add kimi web subcommand to open the daemon-hosted browser UI\n- refactor kimi daemon to start in background by default; add --foreground flag\n- serve web assets from daemon via new registerWebAssetRoutes\n- copy kimi-web build output into CLI bundle at build time\n- update docs for daemon and web commands\n- add unit tests for daemon and web command handlers
UI/UX:
- Onboarding: welcome + language/theme prefs (Modern default, applied on start)
- Modern is the default theme; chat surface white; floating dock (input on top,
status controls as functional pill-buttons below, ctx far right)
- Single-line composer with smaller send; empty-chat hint vertically centered
- Global connecting splash on first load; overlay drift fixes (viewport-unit sizing)
- Wide-screen reading-column cap; font-size pass (chrome up, chat = session list)
- Merged ~/files + ~/diff into one tab (Changed|All, list/tree)
- ThinkingBlock capped to ~3.5 lines with auto-scroll-to-latest
- Workspace rail title + branch on second line
Design system:
- Radius scale tokens (--r-xs/sm/md/lg = 6/8/12/16); unified component radii
- Moved Modern per-component overrides to global style.css (scoped :global() did
not win the cascade — input/tabs/cards were silently un-styled)
- docs/design-system.html: tokens + live component reference
Backend wiring:
- POST /sessions/{id}/profile for model + runtime (thinking/permission/plan)
- GET /sessions/{id}/status; :compact / :fork; agent.status.updated
- Historical replay no longer re-streams (messagesToTurns dedup)
- Register the yuandian_law (元典法律数据库) data source for Chinese
laws/regulations and judicial case search.
- Append a request-id / tool-call-id trace line to every tool result so
failures can be correlated with backend logs.
- Fix the documented MCP tool names in SKILL.md (-data -> _data).
- Also includes the dev marketplace-server env isolation fix in dev.mjs.
Co-authored-by: qer <Anna_Knapprfr@mail.com>
Fires an observation-only Interrupt event when a turn is aborted by the user (e.g. pressing Esc). Previously neither Stop nor StopFailure fired on interrupt, so external tooling that tracks status from hooks stayed stuck on a working state.
* fix: align datasource plugin environment
* refactor: inject managed Kimi env into all stdio plugins
Pin the datasource credential-name test to the canonical
resolveKimiCodeOAuthKey so a digest drift in the standalone plugin
fails CI, and drop the hardcoded plugin-name special case so every
stdio plugin receives the active managed Kimi base URL / OAuth host
consistently (process.env and KIMI_CODE_HOME are already shared with
all plugins).
Installed plugins whose marketplace version is newer than the local
version now render an `update <local> → <latest>` badge and update in
place on Enter; up-to-date plugins show `installed · v<version>`.
Dev-server and CDN-build marketplace generation now stamp each entry's
version from the plugin manifest so the advertised "latest" stays accurate.
Adds a pure computeUpdateStatus() (semver, no spurious downgrades) with tests.
Co-authored-by: qer <Anna_Knapprfr@mail.com>
* Refactor theme
* custom theme support
* docs: add custom themes guide
Document the custom theme file location, the color token reference, selecting a theme via /theme and tui.toml, and fallback behavior. Link it from the customization sidebar and the tui.toml theme field.
* feat(skill): add built-in custom-theme skill
Guides the model (or a manual /custom-theme run) to author a theme JSON in ~/.kimi-code/themes/: docs token reference, deliberate color choices, hex validation, and how to apply via /theme or /reload-tui. Note in the write-tui skill to keep the token set in sync across colors.ts, the schema, the docs, and this skill. Enrich the custom-theme changeset to cover all three usage paths.
* chore: remove theme research report
* fix(tui): resolve lint errors after main merge
Remove unused chalk/currentTheme/ResolvedTheme imports left by the theme refactor; break the theme <-> pi-tui-theme import cycle by dropping the markdown/editor theme getters from the Theme class (consumers call createMarkdownTheme directly); fix unused vars/params, a floating promise, and a redundant union type.
* fix(tui): address custom theme review feedback
- await applyTheme before refreshing terminal theme tracking, so
switching to "auto" installs the watcher against the new state
- invalidate the transcript on automatic (terminal-driven) theme
changes so already-rendered entries repaint
- rebuild UsagePanel bodies on invalidate (previously a no-op); /usage,
/status, /mcp and /plugins now repaint on a theme switch
- repaint the compaction header on invalidate
- validate a custom theme before applying it from the /theme picker
- hide reserved dark/light/auto names from the custom theme list
- escape the theme name when writing tui.toml
- stop the custom theme loader writing warnings to the raw terminal
- remove a stray hello.ts
* refactor(tui): polish custom theme feature
- footer and todo-panel read the currentTheme singleton directly at
render time instead of caching a palette copy; drop their setColors
methods and the manual setColors calls on every theme change
- support "base": "dark" | "light" in custom theme files so a partial
light theme inherits the light palette for unspecified tokens
- reconcile the docs and the custom-theme skill with the silent
invalid-color fallback (no terminal warning)
* refactor(tui): live-repaint the agent swarm progress panel
Read the currentTheme palette through a getter instead of caching it at
construction time, so the swarm progress panel recolors on a theme switch
like the rest of the transcript. Drops the now-unused `colors` option.
* chore: remove plan.md
* docs: update custom theme guide
* docs: document custom theme skill command
* fix(skill): make custom theme user-triggered only
* docs: merge Kimi Datasource into plugins page and add terminal tip to getting started
- Merge datasource.md content into plugins.md as a dedicated section,
placed between installation management and plugin manifest sections
- Replace verbose feature tables with scenario-driven use cases and a
condensed coverage table
- Add /skill:kimi-datasource as an explicit invocation method alongside
natural language; update /new references to /reload
- Promote GitHub URL formats and notes to named H3 subsections within
installation management
- Add terminal recommendation tip (Kitty / Ghostty) in the Installation
section of getting-started
- Remove standalone datasource.md sidebar entries from zh and en nav
* docs: remove stale datasource pages and add redirects to plugins
Delete zh/en datasource.md (content now merged into plugins.md) and
add VitePress redirects so existing bookmarks and search results for
/customization/datasource land on /customization/plugins instead.
* docs: restore datasource pages as forwarding stubs
Replace deleted files with minimal pages that link to the merged
section in plugins.md. VitePress redirects only fire in SSG builds;
dev-server visitors hitting the old URL would 404 without these stubs.
* docs: add dev-server redirect middleware for removed datasource pages
VitePress `redirects` config only fires during SSG build; the dev
server ignores it, causing 404s on the old /customization/datasource
URLs. Add a Vite `configureServer` middleware that handles the redirect
in dev mode, while the top-level `redirects` config continues to
generate meta-refresh HTML pages for the production build.
---------
Co-authored-by: qer <wbxl2000@outlook.com>
* docs: expand AGENTS.md with reader personas, format decisions, and checklist
Add documentation writing principles that were missing from the existing guide:
- Readers: two audience types (technical vs non-technical) with writing targets
- Authoring workflow: think before rewriting (understand → structure → fill)
- Kimi platform rules: strict separation of api.kimi.com vs api.moonshot.cn URLs
- Typography: forbid four-colon callout syntax (::::), note no nesting
- Writing style: one-idea-per-paragraph, map-before-detail structure, clarify
when to use lists vs prose (avoids confusion between 'no fragmentation'
and 'parallel content needs formatting')
- Format decisions: explicit rules for ordered list / unordered list / table / prose
- Cross-references: when links are required, anchor precision, inline vs next-steps
- Page structure: standard template and banner placement rule
- Content completeness: default to keeping everything, omissions need stated reasons
- Checklist: format violation quick-reference and Kimi-specific consistency checks
All existing rules are preserved unchanged (0 lines removed).
* docs: address review comments on AGENTS.md
- Fix "next steps" rule contradiction: replace blanket ban with "no nav
tip blocks"; `## Next steps` is allowed when related pages exist
- Fix checklist Base URL pointer: was pointing to locale index.md
(which has no platform table); now links to Kimi platform rules above
- Fix callout syntax rule: `::::` is valid as an outer nested fence
when correctly closed; ban only unclosed/mismatched fences
- Fix checklist code block rule: carry forward the existing exception
that natural-language prompt examples may omit the language tag
---------
Co-authored-by: qer <wbxl2000@outlook.com>
* feat(acp-adapter): support embedded resource prompts
- advertise embeddedContext support in ACP capabilities and docs
- convert file:// resource_link blocks into decoded paths with optional line ranges
- keep XML wrappers for non-file or unparseable resource_link URIs
- update adapter tests for the new resource link behavior
* feat(acp-adapter): add ACP built-in slash command routing and UNC path support
- add local execution for /compact, /status, /usage, /mcp, /tasks, /help in ACP sessions
- surface unknown slash commands as local errors instead of forwarding to model\n- export ACP_BUILTIN_SLASH_COMMANDS from acp-adapter for CLI reuse
- fix file:// URI conversion for Windows UNC paths
- rebuild agent builtin tools on session tool kaos rebind
* feat: honor HTTP_PROXY/HTTPS_PROXY/NO_PROXY for all outbound traffic
Install a global undici dispatcher at CLI startup so every in-process fetch
(LLM APIs, MCP HTTP, web tools, telemetry, sign-in, update checks) honors the
standard proxy variables, and propagate NODE_USE_ENV_PROXY to spawned stdio
MCP child processes. Loopback hosts always bypass the proxy; an invalid proxy
URL is reported and ignored rather than aborting startup.
* feat: support SOCKS proxies via ALL_PROXY
Recognize SOCKS proxies (socks5/socks5h/socks4/socks alias) from ALL_PROXY or a
socks-scheme HTTP(S)_PROXY, routing traffic through a custom undici connector
backed by the socks client (reusing undici's own TLS handling for https).
HTTP(S) proxies keep precedence; NO_PROXY and loopback are honored for the SOCKS
path too. Child stdio MCP node processes honor HTTP(S) proxies via
NODE_USE_ENV_PROXY; SOCKS applies to the main process only.
* fix: address proxy review comments (env masking, child NO_PROXY, nix hash)
- Resolve HTTP(S)_PROXY explicitly via the first non-blank casing so a blank
lowercase var can no longer mask a populated uppercase one (the dispatcher
installed but went direct), and coerce a SOCKS-scheme value sitting in an
HTTP(S) var to '' so it is never handed to EnvHttpProxyAgent.
- Reconcile a child's NO_PROXY override across both casings using the first
non-blank value run through resolveNoProxy, so a per-server config override
is not shadowed by the injected lowercase value, keeps the loopback bypass,
and passes '*' through verbatim.
- Update flake.nix pnpmDeps hash for the added socks/undici dependencies.
* fix(proxy): honor http ALL_PROXY, match port-qualified NO_PROXY, note child Node version
- Honor an http-scheme ALL_PROXY as the catch-all fallback for both http and
https (scheme-specific HTTP(S)_PROXY still wins), so an ALL_PROXY-only setup
no longer installs a no-op dispatcher and connects direct.
- Make the SOCKS-path NO_PROXY matcher port-aware: a `host:port` entry now
matches only that port (with IPv6-safe parsing for `::1` / `[::1]:443`).
- Document that child stdio MCP proxying via NODE_USE_ENV_PROXY only applies on
Node versions that support it (>= 22.21 / >= 24.5).
* fix(proxy): IPv6 + wildcard NO_PROXY and per-server child proxy edges
- Strip IPv6 brackets from a SOCKS proxy host (e.g. ALL_PROXY=socks5://[::1]:1080)
so the socks client connects to the bare address.
- Add the bracketed [::1] to the loopback bypass: undici's EnvHttpProxyAgent
only exempts IPv6 loopback when the NO_PROXY entry is bracketed (it mis-parses
bare ::1). The SOCKS-path matcher normalizes brackets on both sides.
- Match *.domain wildcard (and host:port) NO_PROXY entries in the SOCKS matcher.
- Compute the child stdio proxy env from the MERGED env so a proxy declared only
in a server's config.env also enables NODE_USE_ENV_PROXY.
* fix(proxy): synthesize HTTP(S)_PROXY from ALL_PROXY for child processes
proxyEnvForChild now hands spawned stdio MCP children the resolved
HTTP_PROXY/HTTPS_PROXY (in both casings), synthesizing them from an http-scheme
ALL_PROXY when no scheme-specific variable is set. Node's --use-env-proxy reads
HTTP_PROXY/HTTPS_PROXY (not ALL_PROXY), so an ALL_PROXY-only parent now proxies
the child consistently with the main process. Shared resolveHttpProxyUrls helper
is reused by createProxyDispatcher and proxyEnvForChild.
* chore(changeset): tighten proxy changeset wording
* docs: fix code fence language and add cross-references (zh/en)
- slash-commands: add 'sh' language tag to /goal example code block
- config-files: link experimental section to env-vars#runtime-switches
- env-vars: link KIMI_CODE_EXPERIMENTAL_* rows to config-files#experimental
* docs: improve goals.md formatting and clarity (zh/en)
- Merge redundant opening paragraphs into one with concrete examples
- Use colons before code examples (not periods)
- Bold state names in lifecycle list (complete/paused/blocked)
- Replace prose keyboard shortcut description with table
- Remove draft product-background text from EN queue section
* docs: move goals after sessions in sidebar (zh/en)
Goal mode builds on multi-turn sessions, so it reads more naturally
after the sessions page in the guides navigation.
* feat(env): migrate kimi-cli model request params and auto-update toggle
Migrate still-relevant environment variables from kimi-cli:
- KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P: sampling params applied
globally to any kimi provider (not tied to KIMI_MODEL_NAME).
- KIMI_MODEL_THINKING_KEEP: Moonshot preserved-thinking passthrough
(thinking.keep), injected only while Thinking is on.
- KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE):
fully disables the update preflight.
Wires env -> provider in Agent.get llm() via applyKimiEnvGenerationParams,
reusing kosong's existing GenerationKwargs / thinking.keep support.
KIMI_MODEL_MAX_TOKENS is intentionally untouched: it already flows through
the completion-budget path.
* fix(env): apply Kimi sampling params to compaction requests too
Sink KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P into ConfigState.provider so
every request built from config.provider — main loop and full-history
compaction alike — carries them, matching kimi-cli where these live on the
shared create_llm provider. thinking.keep stays in Agent.llm because it
depends on the runtime thinking state (compaction runs thinking-off and
correctly skips it).
Splits applyKimiEnvGenerationParams into applyKimiEnvSamplingParams (applied
at provider construction) and applyKimiEnvThinkingKeep (applied in Agent.llm).
Addresses PR review feedback about compaction requests bypassing the wrapped
provider.
