- remove defaultServicesModule() and services/src/module.ts; consume getSingletonServiceDescriptors() directly\n- update daemon service registrations and bootstrap to use registry descriptors\n- add DisposableMap, DisposableSet, disposable tracking, and disposeOnReturn to agent-core DI\n- update AGENTS.md with new registration patterns
- make InstantiationService.services private to prevent external mutation\n- add serviceOverrides to DaemonStartOptions for test injection\n- refactor e2e tests to use startup overrides instead of post-boot container hacks
- move InstantiationType to extensions module; change SyncDescriptor0 to interface\n- add _strict mode and spread args to invokeFunction\n- construct parent-owned descriptors in parent scope\n- materialise delayed services in child scope with global graph tracking\n- update TestInstantiationService ctor and tests for new semantics
- replace scenario 06 with dedicated 06-09 files for model catalog, session children, pending recovery, and image file prompts\n- add prompt execution coverage for parent and child sessions\n- update README scenario index
- Add POST /api/v1/sessions/{session_id}:undo endpoint\n- Add undo request/response schemas and SESSION_UNDO_UNAVAILABLE error code\n- Refactor OpenAPI transforms to support fork, compact, and undo actions\n- Implement SessionService.undo with history validation and compaction boundary guards\n- Add E2E and unit tests for undo endpoint and service logic
- restructure daemon/services DI wiring and lifecycle events
- add session, workspace, model catalog, file, and reverse-RPC REST APIs
- add daemon e2e package with structured scenarios and HTML trace reports
- polish kimi-web rendering, mobile layout, diff view, and session UX
Add an optional `identity` field to HarnessBridgeOptions and default-wire
`kimiRequestHeaders` (User-Agent + X-Msh-Platform/Version/Device-Id) plus
`appVersion` from it. Without these the daemon-hosted KimiCore made
outbound fetches with the Node default User-Agent and the managed
Kimi-for-Coding endpoint rejected with 40340 ("only available for Coding
Agents such as Kimi CLI, …"). The in-process TUI path was unaffected
because SDKRpcClient already synthesised the same headers from its own
identity. Explicit `kimiRequestHeaders` / `appVersion` still win.
apps/kimi-code wires this through its `daemon` subcommand using the
existing `createKimiCodeHostIdentity(version)` helper, and ships a small
`dev:daemon:restart` press-Enter-to-respawn helper so the dev loop can
pick up a fresh build without manually killing the lock-holder.
- default-construct KimiAuthFacade in HarnessBridge when caller omits resolveOAuthTokenProvider\n- stop synthesized always-throw AUTH_LOGIN_REQUIRED closure after device-code login\n- remove tsx watch from dev:daemon to avoid restart loops\n- ignore Docker artifacts in .gitignore\n- add regression test for default resolver wiring
- 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>
* feat: search slash command aliases in autocomplete
Slash-command name completion now matches aliases and shows them in the
label as `name (alias1, alias2)` when the match came from an alias.
Argument completion resolves aliases too. The intercepted completion
keeps the inner provider's conventions: argument hints stay in the
suggestion description, and primary-name matches outrank alias matches
on score ties.
* feat: wrap autocomplete descriptions onto up to two lines
Long slash command / skill descriptions used to be truncated to a single
line in the completion menu. CustomEditor now swaps the slash menu's list
for a WrappingSelectList that wraps descriptions to at most two lines,
ellipsizing past the second; non-slash completion keeps pi-tui's
single-line list.
Plain-text truncations also strip the trailing ANSI reset that pi-tui's
truncateToWidth appends — embedded inside the theme colouring it reset
the rest of the row, so a selected row with a truncated name rendered
its two description lines in different colours.
* chore: make changeset wording user-facing
* style: pass optional description directly instead of conditional spread
Follows the AGENTS.md convention for optional object properties.
- Add terminating-state guard to skip ERR_STREAM_PREMATURE_CLOSE when a process is killed or times out
- Ensure timeout/kill reason is reported instead of the internal stream error
- Add changeset for agent-core and kimi-code
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.
* feat(kosong): support claude-fable-5 adaptive thinking
claude-fable-5 only accepts thinking: {type: "adaptive"} with
output_config.effort; the legacy enabled/budget_tokens config and an
explicit disabled config both return HTTP 400.
- Parse the fable family in Claude model ids (major-only version)
- Route fable >= 5 to adaptive thinking; allow xhigh effort
- Omit the thinking field entirely when thinking is off on fable
- Register the 128k output ceiling and thinking/vision capability
* update .changeset
Updated the configuration to use adaptive thinking for Claude Fable 5 support.
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
---------
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
* 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
