Resuming a session that was already in plan mode with --plan crashed with
"Already in plan mode": the resume path called setPlanMode(true)
unconditionally while session replay had already restored the active plan
state. Check the session status first and only enable plan mode when it is
not active yet, in both the resume startup path and the startup session
picker.
The /sessions picker shared the same onSelect callback, so startup flags
were also re-applied on every mid-session switch, overriding the picked
session's own persisted modes. Gate the flag application behind an
applyStartupModes option that only the startup picker enables, and surface
post-switch setup errors instead of leaving them as unhandled rejections.
* feat(providers): sync custom registry providers on startup refresh
- group registry providers by URL and retry available API keys\n- automatically add new providers and remove disappeared ones\n- coalesce duplicate source URLs to avoid false config-change reports\n- clear defaultThinking when default model is removed\n- update docs and add tests for registry sync scenarios
* fix(tui): only show provider refresh status for added models
Skip removed / metadata-only provider updates when reporting model list changes.\n\n add: test to enforce the behavior.
iTerm2 interprets any OSC 9 payload as a desktop notification, so the
ConEmu-style 9;4 progress sequence (re-sent every second by the progress
keepalive) flooded users with notifications. Only emit progress on
terminals known to implement OSC 9;4: Windows Terminal, ConEmu, Ghostty,
and WezTerm.
* feat(config): tolerate invalid config.toml sections instead of failing startup
Schema errors now drop only the offending sections (single entries for
providers/models) with a warning, so a typo no longer prevents startup or
drops the login state. TOML syntax errors still fail fast with the parse
location. Mid-run reloads keep the last good config when the file breaks.
Warnings surface via the new getConfigDiagnostics API: as a startup notice
in the TUI, on stderr in print mode, and in the status bar after /new.
Write paths stay strict so a broken file is never silently rewritten, and
now fail with a short actionable message instead of raw validation JSON;
the /provider TUI flow and the kimi provider CLI report these errors
instead of crashing on an unhandled rejection.
* fix(config): keep entry-keyed sections when one entry has multiple issues
A providers/models entry with several validation issues was deleted by the
first issue, and the remaining issues from the same safeParse pass then
escalated to deleting the entire section — one badly-typed custom provider
could drop every provider, including the managed OAuth login. Issues on
entry-keyed sections now only ever target the entry itself; once it is
gone, later issues are no-ops.
* 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
Map the /models three-state supports_thinking_type field ('only' /
'no' / 'both', taking precedence over the legacy supports_reasoning
boolean) onto the existing always_thinking capability:
- oauth: parse the field in both /models parsers; 'only' emits
always_thinking alongside thinking, 'no' suppresses thinking even
when supports_reasoning is set, absent falls back to the legacy
boolean. Default thinking selection is forced on for 'only' (and
off for 'no') models during login and provider refresh
- TUI: render the thinking control with a fixed On/Off layout — locked
models show a greyed-out "Off (Unsupported)" segment, and
non-thinking models mirror the style with "On (Unsupported)"
- agent-core: clamp thinkingLevel at the getter so a stale
thinking-off config can never reach the request builder, status
events, or subagent inheritance
- acp-adapter: derive alwaysThinking from capabilities, collapse the
thinking select to a single locked "on" entry, and ignore off
requests for locked models while re-emitting the snapshot
* chore: ignore .worktrees directory
* feat: add tips banner below welcome panel on startup
- Fetch active/fallback tips from the configured CDN with a 3s timeout.
- Filter tips by semver, client version, and date range.
- Render the banner directly below the welcome panel on startup/resume.
- Support tag, multi-line text, subtext, automatic wrapping, and narrow-terminal safety.
* refactor(tui): use theme color methods in banner component
Replace raw chalk calls with currentTheme helpers: tag uses
boldFg('primary'), main text uses boldFg('textStrong'), and subtext
uses fg('textDim') without stacking the dim modifier on the already
dim shade. Strengthen tests to assert the exact themed ANSI output.
- custom-theme.md, update-config.md, mcp-config.md now resolve KIMI_CODE_HOME first.
- custom-theme.md requires clarifying intent before creating or editing themes.
- custom-theme.md falls back to plain-text questions in auto mode.
* 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>
- 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.
