* feat(tui): reveal full bash command on ctrl+o expand
The Bash tool header truncates long commands at 60 chars and the
result renderer never showed the command body, so the full command
was nowhere to be found in the UI. When the user expands the card
with ctrl+o, render the complete multi-line command above the
output.
* feat(tui): wrap long text in AskUserQuestion dialog instead of truncating
Replace single-line truncation with hanging-indent word wrap for the
question prompt, body description, option label, option description,
and submit-tab review entries. Long content now flows onto multiple
rows instead of being cut off with an ellipsis.
* fix(tui): cap todo panel at 5 rows with overflow indicator
Pick visible todos around in_progress (recent done + upcoming pending),
append `+N more` when truncated.
* fix(tui): make todo selector order-agnostic
The previous selector assumed todos were grouped as done...pending
when no in_progress existed. On interleaved orderings (the TodoList
tool keeps the model-provided order without normalizing) the before
and after windows skipped most candidates and produced fewer than
five rows. Pick directly from status buckets instead.
* fix(approval): include file content and diff in approval display
After #26 the WriteTool/EditTool input display was reduced to
`{kind: 'file_io', operation, path}`, dropping the args carried by the
previous generic fallback. The approval panel then only had a path to
show — no file content for Write, no diff hunk for Edit — and ctrl+e
expanded to the same one-liner.
Extend the file_io display with optional `content` / `before` / `after`
fields so Write can attach its full content and Edit can attach its
old_string/new_string hunk. The adapter promotes file_io+content to a
file_content block and file_io+before/after to a diff block, matching
what the panel renders for the legacy generic-fallback path.
* feat(tui): open full-screen viewer for approval previews
Inline ctrl+e expand-in-place inflated the approval panel past one
viewport for any non-trivial Edit / Write, which collided with pi-tui's
inline differential renderer and the terminal's "snap to bottom on
stdout" reflex: scrolling back glitched and the screen flickered. On
top of that, the diff renderer's O(m·n) LCS DP ran every frame the
panel was visible, so each spinner tick re-paid the cost.
Make ctrl+e hand off to a dedicated full-screen viewer instead. The
viewer renders all body lines once at construction and slices them on
scroll, so per-frame cost is O(viewport) regardless of payload size.
It uses the same nested-takeover pattern as TaskOutputViewer; the
approval panel instance is preserved and refocused on close so the
selection / feedback state survives.
The panel itself drops its local `expanded` toggle and always renders
the compact cluster view; ctrl+e now exclusively forwards to the host
when there is something to preview, and falls through to the existing
plan-expand toggle otherwise.
* chore(changeset): restore approval previews
* feat(tui): expand paste markers on second paste
When the cursor sits on a folded paste marker (e.g. `[paste #1 +15 lines]`)
and the user pastes again (Ctrl-V or bracketed paste), the marker is expanded
back to its original content instead of inserting new clipboard data.
* chore: add changeset for paste marker expansion
* fix(tui): preserve paste content after marker expansion for undo
Stop deleting the paste entry from the Map after expansion so that
undo → re-expand still works.
* fix(tui): buffer consumed paste data to handle split end sequences
Accumulate chunks while consuming discarded paste data so a
split ESC[201~ across chunks still resets consumingPaste.
Add reference table entries for the new in-TUI export commands, and
extend the Sessions guide so users can discover them alongside the
existing `kimi export` CLI subcommand. Mirrored across en and zh.
* feat(tui): add /export-md slash command
Add a new /export-md (alias: /export) command that exports the current
session conversation as a human-readable Markdown file. The export
includes YAML frontmatter metadata, an overview section, and
turn-by-turn dialogue with collapsible thinking blocks and tool
call/result details.
Also exposes Session.getContext() on the SDK to allow TUI-layer access
to the agent's conversation history.
* chore: add changeset for /export-md
* fix: use static imports instead of dynamic imports in handleExportMdCommand
* chore: simplify changeset wording
* feat(tui): add /export-debug-zip slash command
Add a new built-in slash command that exports the current session as a
debug ZIP archive directly from the TUI, mirroring the existing
`kimi export` CLI behavior.
Extract `detectShellEnvironment` into a shared utility to eliminate
duplication between the CLI export handler and the new TUI command.
* chore: add changeset for /export-debug-zip
* refactor: extract toTerminalHyperlink into shared utility
Make the exported ZIP path clickable in terminals that support OSC 8
hyperlinks (iTerm2, Terminal.app, VS Code, etc.). Also deduplicate
the helper that was copy-pasted in plan-box.ts.
* fix: stop thinking spinner leaking past turn end on empty deltas
When a provider emits an empty thinking delta (e.g. Anthropic
signature_delta -> think: ""), a ThinkingComponent was created with a
running spinner but thinkingDraft stayed empty. Subsequent calls to
flushThinkingToTranscript guarded on thinkingDraft.length and
returned early without calling onThinkingEnd(), leaking the spinner
past the turn end.
Two fixes:
- onThinkingUpdate: skip component creation for empty text when no
existing component needs updating (source prevention).
- flushThinkingToTranscript: finalize any orphaned component even
when thinkingDraft is empty (defensive cleanup).
* chore: add changeset for thinking spinner fix
* refactor(tui): simplify flushThinkingToTranscript
---------
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
* feat(export): record install source and shell environment in manifest
Capture how the CLI was installed (npm-global, native, etc.) and the
user's terminal environment (TERM, TERM_PROGRAM, multiplexer, SHELL)
so exported session archives carry richer diagnostic context.
* chore: add changeset for export manifest enhancements
* chore: simplify changeset description
* fix(agent-core): always pair tool.call with tool.result on malformed returns
A tool returning undefined, a primitive, or an object without a valid
output field crashed normalization, exited the batch loop without
dispatching the matching tool.result, and left the next provider
request to fail with a missing tool_call_id response.
- Validate the tool return at the boundary in runRunnableToolCall via a
new coerceToolResult helper; malformed returns become an isError
result.
- Harden normalizeToolResult and toolResultStopsTurn against
non-conformant input from synthetic results or finalize hooks.
- Track unpaired tool.call ids in runToolCallBatch and emit
compensating error results in finally for any that did not receive a
result.
* refactor(agent-core): simplify tool result pairing
Drop the unpairedCallIds tracking and finally-compensation wrapper from
runToolCallBatch. The set was updated before dispatchEvent, so a failure
between the two left it inconsistent; the per-call try/catch already
produces a paired error result, making the outer wrapper redundant.
Coerce hook returns at the synthetic and finalizeToolResult boundaries
so a malformed hook output is normalized into a paired error result the
same way a malformed tool return already is.
* fix(kimi-code): exit promptly when the controlling terminal dies
Register SIGHUP/SIGTERM handlers and stdout/stderr 'error' listeners on
KimiTUI startup. SIGHUP and EIO/EPIPE/ENOTCONN writes both indicate the
terminal is gone; under those conditions the normal cleanup path keeps
writing restore sequences that re-fire the same EIO and can pin a CPU
core indefinitely. The new emergencyTerminalExit() path skips cleanup
and exits 129 immediately. SIGTERM still routes through the graceful
stop() path so telemetry and session state flush normally.
* fix(kimi-code): emergency-exit when SIGTERM graceful shutdown rejects
The SIGTERM handler previously did `void this.stop()`, so a rejection
from `closeSession()` or `harness.close()` was swallowed and could leave
the process hanging on pending I/O (the latch on `isShuttingDown` also
makes any further graceful exit attempt a no-op). Chain a `.catch()` so
a failed graceful shutdown falls through to `emergencyTerminalExit()`
and the process exits with 129 instead of waiting for SIGKILL.
* fix(kimi-code): preserve 128+signum exit code for signal-driven shutdown
Installing a SIGTERM listener suppresses Node's default termination,
which would have exited 143. With the previous handler, externally
terminated TUIs routed through `onExit()`'s default `exitCode = 0` and
reported success to supervisors keying off non-zero on signal exits.
Thread an optional `exitCode` through `stop()` → `onExit()`, parameterize
`emergencyTerminalExit()`, and have the SIGTERM handler pass 143 down
both the success and failure paths. SIGHUP and dead-terminal write
errors still exit 129 (the SIGHUP convention). User-initiated `/exit`
keeps its 0 default since `stop()` is called without an `exitCode`.
* fix(kimi-code): unregister signal handlers when start() throws
Signal and stdout/stderr 'error' listeners were installed at the top of
start() but never rolled back when initMainTui() or finishStartup()
threw. Retrying start() in the same Node process (tests, embedded use)
accumulated listeners on `process` and would eventually trip
MaxListenersExceededWarning or run shutdown logic multiple times.
Wrap the whole start() body in a try/catch so any thrown error
unregisters the listeners before propagating. Inner catch blocks still
own focus/theme/UI cleanup; this only adds the listener half.
* fix(kosong): make OpenAI-compatible thinking work without reasoning_key
Reasoning field names (reasoning_content / reasoning_details / reasoning)
are protocol facts, not user preferences. Treating reasoning_key as a
required user-set field meant any path that didn't go through the catalog
— hand-written config.toml in particular — silently lost thinking content
and broke strict gateways like DeepSeek.
Demote reasoning_key to an internal protocol constant with an explicit
override:
- Inbound (stream + non-stream): scan reasoning_content,
reasoning_details, reasoning in order; first string value wins. An
explicit reasoning_key restricts the scan to that one field.
- Outbound: serialize ThinkPart back as reasoning_content by default.
An explicit reasoning_key writes to that field instead.
- reasoning_effort auto-injection no longer requires reasoning_key;
presence of ThinkPart in history is enough.
Catalog plumbing is unchanged — explicit values from the catalog still
win, the default just stops being undefined.
Manually verified end-to-end against the real DeepSeek API with a
hand-written config.toml that does not set reasoning_key: thinking
content renders, no 400, multi-turn conversations work.
* fix(kosong): normalize blank reasoning_key to unset
ModelAliasSchema accepts `reasoning_key = ""` (z.string().optional()).
A blank value used to disable the default field scan and route both
inbound reads and outbound writes through an empty property name.
Trim and treat empty as undefined at the provider boundary so the
default protocol behavior applies.
* fix(kosong): preserve caller-pinned reasoning_effort during auto-inject
When the history contains ThinkPart, generate() injects
reasoning_effort='medium' and then assigns it onto createParams,
which used to silently overwrite a value the caller set via
withGenerationKwargs({ reasoning_effort: 'high' }). Skip auto-inject
when an explicit reasoning_effort already lives in kwargs.
* fix(tui): cap Write preview at args-finalize to preserve terminal scrollback
The Write tool preview rendered the full file content between args-finalize
and result, then snapped to the 10-line collapsed cap once the result landed.
That large shrink triggered pi-tui's full-redraw path, which emits \x1b[3J
and wipes the terminal scrollback (including history from before TUI start).
Cap the preview as soon as args finalize so the rendered height stays stable
across the args-finalize → result transition, avoiding the full redraw.
* chore: update changeset message
* feat(kimi-code): pick provider when running /logout
/logout used to clear the credential tied to the currently selected
model, which made the target invisible and coupled logout semantics to
model selection. It now opens a picker over every credential currently
held and highlights the active model's provider so pressing Enter
matches the previous behavior.
* feat(kimi-code): alias /logout as /disconnect
So users who entered a provider via /connect can leave it with the
symmetric /disconnect.
* fix(kimi-code): keep /logout usable for stale managed config and unrelated providers
- Surface the Kimi Code OAuth entry in the picker whenever
config.providers still references it, not only when a live token is
present. auth.logout cleans the config either way, so stale entries
can no longer become unreachable through /logout.
- When the picked provider is not the one backing the current model,
just refresh the provider/model listing and leave the session and
model selection alone. Full teardown stays for the case where the
active provider was the one being removed.
* feat(agent-core): re-export wire record types for in-monorepo consumers
* chore(vis): purge legacy wire protocol code
* feat(vis): introduce single-source agent-record types
* test(vis): add fixture session and builder helper
* feat(vis): implement new session store reader
* feat(vis): wire new session list/detail routes
* refactor(vis): drop legacy path config
* feat(vis): adapt session list page to new DTO
* feat(vis): implement per-agent wire reader
* feat(vis): rewrite wire route for new protocol
* feat(vis): rewrite wire type metadata for new protocol
* feat(vis): rewrite wire row + headline for new record union
* feat(vis): wire tab detail panel + multi-agent selector
* feat(vis): rebuild wire issues detection for new protocol
* feat(vis): implement context projector
* feat(vis): rewrite context route on projector
* feat(vis): rebuild context tab for new ContextMessage shape
* feat(vis): implement agent tree builder
* feat(vis): rewrite agents route
* feat(vis): rebuild subagents tab around state.json.agents
* feat(vis): rebuild state tab on raw state.json
* chore(vis): purge residual legacy field references
* vis: rewrite complete on new agent-core protocol
* fix(vis): adapt to wire protocol 1.1 with flattened tool calls
* fix(vis): populate workDir from session index
* fix(vis): return broken-state sessions from detail lookup
* fix(vis): tolerate per-session wire read failures during listing
* fix(vis): read wire files from canonical session path
* feat(vis): restore session detail page with full tab layout
* feat(vis): wire subagent context tab to real ContextTab
* fix(vis): sync wire and context tab agentId with prop changes
* feat(vis): auto-pick a free dev port when 3001 is busy
* feat(vis): accept v1.0 wire files via agent-core migration chain
* refactor(vis): default API to 5174 and pick a non-colliding vite port
* feat(vis): make long strings expandable with copy in JsonViewer
* fix(vis): stop gating session health on protocol version
* refactor(vis): split wire records into raw + projected; best-effort unknown protocol
* feat(vis): pair tool.call with tool.result via inline cross-reference and hover highlight
* feat(vis): open session folder and copy its path from the detail header
* fix(vis): reconstruct assistant and tool messages from loop events
* fix(vis): keep system prompt bubble within the message column width
* feat(vis): collapse tool result bubble by default in context view
* feat(vis): expose broken_main_wire in the session health filter
* fix(vis): reset wire and context tab agent when navigating sessions
* fix(vis): fall back to a generic headline for unknown wire record types
* fix(vis): emit compaction summary as an assistant message with origin
* fix(vis): harden session-store reads for broken wires, broken state, and path-traversal agent ids
* feat(vis): inline image previews for image_url content parts
* fix(agent-core): resolve user skills from OS home directory, not kimi home
KimiCore incorrectly used the kimi home directory (e.g. ~/.kimi-code) as
userHomeDir, causing the skill scanner to look for user skills under
~/.kimi-code/.agents/skills/ instead of ~/.agents/skills/. Only the
builtin mcp-config skill was found.
Fix by always setting userHomeDir to homedir() (the actual OS home),
independent of the homeDir / KIMI_CODE_HOME options that control where
session data is stored.
* chore: add changeset for skill user home dir fix
* test(node-sdk): align SDK skill test with OS home resolution fix
* Apply suggestion from @liruifengv
Signed-off-by: liruifengv <liruifeng1024@gmail.com>
---------
Signed-off-by: liruifengv <liruifeng1024@gmail.com>
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
* fix(catalog): preserve reasoning fields
* fix(catalog): treat interleaved=true as reasoning_content
models.dev documents `interleaved` as `boolean | { field }`, where the
bare boolean means "general support" without an explicit field name.
The previous branch returned undefined for `true`, leaving openai-compat
gateways that publish `interleaved: true` without a round-tripped
reasoning field. Map `true` to the default `reasoning_content` so those
models still surface and replay thinking content.
* fix(catalog): preserve interleaved field in built-in catalog snapshot
`update-catalog.mjs` drives the bundled catalog that ships with release
builds and is the default source for `/connect`. The allowlist dropped
`interleaved`, so even after the runtime learned to read the field, the
default offline path never sees it — reasoning round-tripping silently
stayed off for openai-compat models in release builds. Keep
`interleaved` so the bundled snapshot carries the same metadata as the
live models.dev catalog.
---------
Co-authored-by: 7Sageer <7sageer@djwcb.cn>
Replace the --flag style (/connect --url=..., /connect --refresh)
with positional arguments and bare keywords:
- /connect https://example.com/catalog.json
- /connect refresh
- /connect (no args, default behavior)
This aligns the slash-command UX with peer CLI tools (claude-code,
pi, opencode) where slash commands use bare words rather than
CLI-style flags.
Closes#30 follow-up
* docs: document /connect command and model catalog
Add a /connect row to the slash-commands reference (English and Chinese)
and a new "/connect and the model catalog" section in providers.md that
covers the bundled catalog, --refresh, --url, and the relationship with
hand-written config.toml entries.
* chore(changeset): trim /connect changesets to user-facing wording
Drop internal phrasing (pruned snapshot, "not gated by models.dev",
fallback mechanics, and the Anthropic catalog base URL path fix that
landed alongside the initial /connect implementation) so the release
notes describe behavior users can observe, not implementation details.
* docs(zh): translate "catalog/flag/endpoint" in /connect section
Rework the Chinese wording for the /connect docs: render "model catalog"
as "模型目录" (with the English term in parentheses on first use), drop
the leftover English "flag"/"endpoint" usage, and smooth out the
translationese in the surrounding sentences.
Update the cross-link anchor in slash-commands.md to match the new
Chinese heading.
* docs(en): tighten /connect wording
Fix the subject/verb mismatch in the /connect step description (the
sentence switched subjects mid-list), replace "endpoint" with the more
accurate "URL" since the catalog source is a static JSON file, and
clarify that /connect is limited to the provider types in the table
above rather than to whatever the catalog happens to cover.
* chore(changeset): keep connect-model-catalog changelog to one line
Defer --refresh, --url, and metadata details to the new docs section
(`/connect` and the model catalog in configuration/providers.md). The
changelog now just announces the command exists.
* fix(cli): fix first launch telemetry timing and extract telemetry init (7 files)
- extract telemetry initialization into cli/telemetry.ts\n- ensure deviceId is created before harness construction for correct first_launch tracking\n- emit session resume hint as meta message in stream-json output format
* feat: add /connect command with models.dev catalog support
Add a /connect slash command that configures a provider and model
from a models.dev-style catalog. Users no longer need to hand-write
model metadata (context window, output limit, capabilities).
Architecture (3 layers):
- kosong: pure data layer — Catalog schema, inferWireType,
catalogModelToCapability
- node-sdk: IO + config write — fetchCatalog, applyCatalogProvider,
catalogModelToAlias
- app: TUI flow — /connect command, provider/model selection,
credential input, config persistence
UI improvements in this PR:
- ChoicePickerComponent: add searchable (fuzzy filter + search bar)
- ModelSelectorComponent: add searchable (same)
- Extract reusable paging.ts for list pagination
Changesets included for kosong, kimi-code-sdk, and kimi-code.
* feat: bundle pruned models.dev catalog for offline /connect
When the network is unavailable, /connect now falls back to a built-in
snapshot of the models.dev catalog.
- `scripts/update-catalog.mjs`: fetches models.dev/api.json, strips
unnecessary fields, and writes `src/built-in-catalog.ts` with the
JSON string as a TS constant.
- `loadBuiltInCatalog(text?)` in node-sdk: parses the JSON string safely;
returns undefined on any failure.
- `handleConnectCommand`: on fetch failure, shows an informative offline
message and tries the built-in snapshot.
- The snapshot file is a placeholder (`undefined`) in source control;
`update-catalog.mjs` populates it before release builds so the actual
catalog is inlined into the bundle by rolldown.
* refactor(tui): share search and pagination across list pickers
ChoicePicker and ModelSelector each carried their own copy of the cursor +
fuzzy-search + pagination state machine. Extract it into a reusable
SearchableList so both pickers share one implementation; behavior is unchanged.
* fix(tui): filter unsupported catalog providers
* docs(tui): clarify /connect stale-alias cleanup depends on removeProvider
* fix(kimi-code): inject built-in catalog at release time
* feat(tui): hint at /login and /connect when /model has no models
Replace the bare "No models configured." error with a notice that
points users to /login for Kimi and /connect for other providers.
* fix(tui): tighten /connect error reporting for edge cases
Two silent-failure cases in /connect could leave users without any
feedback to act on:
- Reject `--url` when its value is missing (e.g. `/connect --url` or
`/connect --url=`). Previously the argument parser silently fell
back to the default catalog, so a malformed flag still appeared to
succeed but with the wrong source.
- Show an explicit error when the resolved catalog yields no providers
with supported wire types. Previously the picker resolved with no
selection and the command returned without any UI feedback.
* chore(tui): restore slash invalid intent type
* fix(tui): support /logout for /connect-configured providers
After /connect writes a non-managed provider (e.g. openai), /logout
fell through to "Nothing to logout." because the handler only matched
the managed default and isOpenPlatformId branches, leaving users no
in-app way to drop the API key and model aliases they just configured.
Collapse the OpenPlatform branch into a generic "provider is present
in config" check so any non-managed provider in config — OpenPlatform
OAuth targets and /connect catalog providers — goes through the same
removeProvider path.
* fix(tui): reject --url values that are not http(s) URLs
`resolveConnectCatalogRequest` previously matched any non-space token
after `--url` as the URL, so `/connect --url --refresh` parsed
`--refresh` as the value and bypassed the missing-value error path.
Bare non-URL tokens (`/connect --url not-a-url`) and non-http(s)
schemes were also silently accepted.
Constrain the captured value to `https?://...` so flag-like and
non-URL tokens fall through to the existing `URL_FLAG_PRESENT_RE`
check and surface a clear error.
* ci(native): scope built-in catalog generation to signed macOS jobs
The catalog-generation step ran whenever `inputs.sign-macos` was true,
including Linux and Windows targets that take the local-profile build
path and never consume the generated catalog. A transient models.dev
outage would therefore fail unrelated artifact builds.
Match the condition to the macOS signed release-profile build that
actually consumes the bundled catalog.
* fix(ci): embed built-in catalog in non-macOS native artifacts
The earlier narrowing to `runner.os == 'macOS' && inputs.sign-macos`
relied on a misread of build.mjs: its `profile === 'release'` guard
only auto-fetches the catalog as a dev fallback. Whether the binary
actually embeds the catalog is decided by tsdown's define at bundle
time, which reads KIMI_CODE_BUILT_IN_CATALOG_FILE regardless of
profile.
Linux and Windows release artifacts therefore lost their bundled
catalog and silently regressed offline /connect on those targets.
Restore generation for all OS jobs when sign-macos is true.
* chore(tui): mention /connect in welcome panel hints
Align the welcome panel with the /model picker so the empty-state copy
points users to both /login and /connect.
