Merge turnId/step into a single `turnStep` field ("0.1") and
attempt/maxAttempts into `attempt` ("2/3"), and drop the
messageCount/toolCallCount fields. The per-request `llm request`
line goes from up to 8 fields down to ~3; the `llm config` line
(including thinkingEffort, logged for all providers) is unchanged.
Nix's profile prepends its bin directory to PATH, shadowing the Node.js version installed by setup-node. Moving Nix installation before setup-node ensures the Node >=24 PATH entry remains first, fixing `ERR_PNPM_UNSUPPORTED_ENGINE` during release.
- Add version:release script combining changeset version with Nix hash update
- Update release workflow to install Nix and use version:release
- Document updated hash refresh workflow in for-agents/workflows.md
- Include changeset for the fix
* docs: simplify plugins documentation
* docs: restore plugin caveats lost during simplification
Re-add three behaviors that were dropped from the simplified plugins
docs: the stdio MCP `cwd` must start with `./`, local-path installs run
from the managed copy (so editing the source after install requires a
reinstall), and `/plugins remove` only deletes the install record while
leaving files on disk. Mirror the changes in both en and zh.
* feat(agent-core): add cron ClockSources abstraction
ClockSources splits wall-clock and monotonic time so the cron scheduler
can be driven by an injected/simulated clock without breaking the lock
heartbeat. resolveClockSources reads KIMI_CRON_CLOCK to switch between
system, env-var-backed, and file-backed wall clocks; monotonic time is
always process.hrtime.bigint() and never overridable.
* feat(agent-core): add 5-field cron expression parser
parseCronExpression handles the standard 5-field syntax with the
cron-style dom/dow OR rule. computeNextCronRun uses field-by-field
jumping (not minute scanning) so sparse expressions like '0 12 1 1 *'
stay fast. hasFireWithinYears caps the search at 5 years so syntactically
legal but never-firing expressions ('0 0 31 2 *') return null instead of
spinning forever — required by CronCreate validation.
* feat(agent-core): add deterministic cron jitter
Recurring jobs shift forward by min(10% of period, 15min); one-shot
jobs landing on :00/:30 shift earlier by up to 90s. Offset is hashed
from task.id so reschedules and restarts stay stable. KIMI_CRON_NO_JITTER
disables both branches for reproducible benches.
* feat(agent-core): add CronTask type and cron prompt origins
CronTask matches what gets persisted to tasks.json (with durable stripped).
CronJobOrigin carries coalescedCount and stale so the agent can react to
collapsed fires without separate channels; CronMissedOrigin tags the
boot-time AskUserQuestion path.
* test(agent-core): guard against Date.now() in cron scheduler files
oxlint 1.59 does not support no-restricted-syntax, so the ESLint-style
guard from the plan is implemented as a vitest scan. The four guarded
files (scheduler/persist/lock/jitter) must route every wall-clock read
through ClockSources.wallNow(); clock.ts is excluded because that is
where the abstraction is defined. Non-existent files are skipped so the
guard activates automatically when later commits introduce them.
* feat(agent-core): add cron telemetry event-name constants
Four event names emitted by later commits (cron_scheduled, cron_fired,
cron_missed, cron_deleted) live with the cron module rather than in the
generic telemetry interface so a typo can't drift the metric and the
abstraction stays domain-free.
* feat(agent-core): add in-memory SessionCronStore
Holds cron tasks scoped to a single CLI session — vanish on exit. Phase 2
will add a file-backed sibling that shares the shape. Ids are 8 hex
characters with a collision-retry cap; createdAt is supplied by the
caller's wall clock so the store stays clock-pure (and exempt from the
Date.now() guard for the same reason).
* feat(agent-core): add session-only CronScheduler engine
The scheduler is a pure callback-driven loop: it gets tasks from a
source(), gates on isIdle()/isKilled?(), computes next fire via
cron-expr + jitter, and invokes onFire with the coalesced count when a
task is due. lastSeenAt is in-memory only — coalesce semantics make a
restart skip acceptable, but persisting last-fire would silently swallow
legitimately-due fires. pollIntervalMs=null lets P1.8 disable the
auto-tick timer for bench scenarios.
* feat(agent-core): add CronManager Agent integration layer
CronManager owns a SessionCronStore + CronScheduler and wires them to
the Agent: scheduler.isIdle reads agent.turn.hasActiveTurn, isKilled
reads KIMI_DISABLE_CRON, onFire builds a CronJobOrigin and routes
through agent.turn.steer. Stale flag is computed on read (7-day age,
recurring only, KIMI_CRON_NO_STALE shorts it) so manager doesn't have
to mutate persisted tasks. handleMissed takes a renderer callback so
P2.7 can plug in the AskUserQuestion text without bringing render
imports into Phase 1.
* feat(agent-core): add CronCreate tool (session-only path)
CronCreate validates the expression, enforces the 5-year fire window
(blocking '0 0 31 2 *' typos), caps prompt bytes at 8KB, caps active
jobs at 50 per session, and rejects durable=true until Phase 2 adds the
file-backed store. Manager exposes emitScheduled/emitDeleted so tools
never reach into agent.telemetry directly.
* feat(agent-core): add CronList tool
Read-only tool surfacing every scheduled cron job for the session. Each
record carries id / cron / humanSchedule / nextFireAt / recurring /
durable / ageDays / stale, formatted in the same key: value\n---\n
shape as TaskList. nextFireAt is the post-jitter timestamp so the model
sees what the scheduler will actually fire on. Malformed cron strings
render with null nextFireAt instead of throwing — defends against any
future direct store inserts.
* feat(agent-core): add CronDelete tool
Validates the 8-hex id shape up front and routes deletion through the
manager so cron_deleted telemetry stays consistent with cron_scheduled.
Not-found is reported as an error so the model corrects itself rather
than silently believing the delete succeeded — the next CronList would
still show whatever id was missed.
* feat(agent-core): wire CronManager + cron tools into Agent
Agent gains a public cron field constructed and started in the
constructor. The scheduler's setInterval is .unref()'d so the cron
timer never keeps the process alive, and isKilled (KIMI_DISABLE_CRON)
short-circuits every tick, so eager start is safe.
ToolManager registers CronCreate/CronList/CronDelete next to the
background tools. initializeBuiltinTools runs lazily after the Agent
constructor finishes, so this.agent.cron is already defined when the
tools are constructed.
* feat(agent-core): add manual-tick env + SIGUSR1 bench hook
KIMI_CRON_MANUAL_TICK=1 forces the scheduler into manual-drive mode
(pollIntervalMs: null), and in the same gate SIGUSR1 binds to a
no-throw manager.tick() so bench scripts can advance the scheduler
with kill -USR1 <pid> without a custom RPC.
SIGUSR1 binding is opt-in (rather than always-on) for two reasons:
the auto-tick interval already advances the scheduler, and a CLI with
many subagents would otherwise pile up listeners and trip Node's
10-listener default. Tests cover the env gate, signal swallowing,
listener cleanup, and the no-bind path when the env is unset. The
AgentTestContext harness gains an onTestFinished cleanup so the
auto-started cron manager never leaks across test files.
* test(agent-core): add end-to-end session cron smoke
Exercises the full Agent → ToolManager → CronScheduler stack through
the production CronCreateTool surface. Local-time anchor + injected
ClockSources make coalescedCount=3 deterministic across host
timezones. A second case walks the Create → List → Delete tool cycle
to confirm the three-tool surface composes round-trip.
* test(agent-core): extract shared cron test harness
Pulls the duplicated createAgentStub + createClocks helpers out of the
five cron test files into test/agent/cron/harness/stub.ts. The shared
stub keeps the lightweight-Agent shape (only turn + telemetry surfaces
need to look real) while letting individual tests opt into the
options that mattered locally (hasActiveTurn / steerReturns).
* test(agent-core): trim cron test file headers
Compresses each cron test header to a couple of lines describing what
the file covers. The long rationale blocks were process documentation
(why-this-file-exists, why-stub-vs-real-agent, plan-doc references)
that didn't help anyone reading the test later. The few details that
mattered (local-time anchor, coalescedCount math) stayed inline next
to the code that needs them. E2E test also picks up the shared
createClocks helper instead of defining its own.
* test(agent-core): convert cron tool output assertions to inline snapshots
The 21 multi-field toMatch / toContain assertions across CronCreate /
CronList / CronDelete tests covered the same ground a snapshot would
have but cost more diff churn when a format detail changes. Errors
become single-line snapshots; success outputs go through a small
scrubCronOutput helper that replaces the random 8-hex id and ISO
timestamp with stable placeholders so the snapshot is deterministic
across TZ and run.
* refactor(cron): remove durable flag, env clock source, and enable cron tools in default profile
- Remove the unimplemented durable persistence field from the entire cron stack (types, tools, manager, tests, docs) to avoid misleading the model into promising cross-session persistence that does not exist yet.
- Drop the env:VAR clock source in favour of the file:path source for test/bench control.
- Register CronCreate, CronList, and CronDelete in the default agent profile.
* fix(agent-core): address PR #136 typecheck and Codex review for cron tools
Typecheck:
- Bracket-access KIMI_CRON_* env reads under TS4111 in cron source/tests.
- Add `approvalRule` to CronCreate/CronList/CronDelete tool executions.
- Guard `cron-expr.detectStep` against undefined array elements; cast the
readonly snapshot in session-store.test through `unknown`; import the
missing `ClockSources`/`ContentPart` symbols in manager.test.
- Extend `isReplayUserTurnRecord` switch to cover the new `cron_job` and
`cron_missed` origins so kimi-code stays exhaustive.
Semantics (from Codex review):
- CronCreate re-reads `wallNow()` and re-checks the session cap inside
`execute()`, so manual-approval delays and concurrent prepared calls
can't backdate the schedule or breach the cap.
- One-shot jitter floors the pull-forward at `task.createdAt`, so a
brand-new `:00`/`:30` reminder can't end up before its scheduling time.
- Scheduler coalesce loop reapplies the same jitter as the delivery path
and advances `lastSeenAt` to the last actually-delivered ideal fire;
a not-yet-due jittered slot is no longer lost. One-shot fires always
report `coalescedCount: 1`.
- Manager removes recurring tasks after the first stale fire and emits a
`cron_deleted` event, matching the 7-day auto-expire contract.
- CronList anchors one-shot `nextFireAt` at `createdAt`, so a pending
today's slot isn't rendered as tomorrow.
Tests cover each of the above and a changeset is added.
* fix(agent-core,tui): address deep review + Codex review on PR #136
Closes the deep-review pass and the four Codex review rounds that
followed on the cron tools feature. Consolidated rather than landed
as a series so the PR history reads as one fix wave on top of the
original Phase-1 cron implementation.
## Lifecycle + structural
- Session.close() now stops every agent's CronManager via
`Promise.allSettled` (mirroring `stopBackgroundTasksOnExit`).
Without this the 1s setInterval and its closure-captured
Agent/Session graph leaked on every closed session.
- Agent constructor gates `cron.start()` and the three Cron tool
instantiations on `type !== 'sub'`. Subagents no longer pile up
empty 1Hz timers or duplicate SIGUSR1 listeners under
`KIMI_CRON_MANUAL_TICK=1`.
## Permission + plan-mode parity
- `PlanModeGuardDenyPermissionPolicy` denies CronCreate and
CronDelete during plan mode (CronList stays allowed); matches the
TaskStop precedent.
- `DEFAULT_APPROVE_TOOLS` includes CronList for parity with TaskList
/ TaskOutput so manual-approval mode doesn't prompt on read-only
listings.
## Cron-fire envelope + projector
- Cron fires wrap `task.prompt` in a `<cron-fire jobId=… cron=…
recurring=… coalescedCount=… stale=…><prompt>…</prompt></cron-fire>`
XML envelope (mirrors `notification-xml.ts`). Without this the
`coalescedCount` and `stale` cues documented in cron-create.md
were invisible to the LLM.
- Projector `isInjectionUserMessage` recognises `<cron-fire ` so the
envelope isn't merged into adjacent real user messages.
- TUI `SessionReplayController.renderUserMessage` skips cron_job /
cron_missed origins (matches `isReplayUserTurnRecord`'s exclusion);
resumed sessions no longer render the raw envelope as user text or
miscount cron records toward the replay turn limit.
## Scheduler invariants
- `tick()` only advances `lastSeenAt` / removes one-shots after a
successful `onFire`. A throw in `agent.turn.steer` previously
silently lost the fire; now the next tick re-detects and retries.
- New `getNextFireForTask(id)` on the scheduler (delegated through
the manager) lets CronList render the same instant the scheduler
will fire. Previously CronList computed from `nowMs` and could
report tomorrow's slot while a current-period jittered delivery
was still pending.
## Cron parser + validation
- `parseCronExpression` now rejects non-cron numeric forms via a
`parseCronInt` helper guarded by `^\d+$` — `''` / `'1e1'` /
`'0x10'` / `'+5'` / `'-5'` no longer silently become 0, 10, 16,
5, or `0-5`.
- `nextRunWithinMinutes` bounds search by a wall-time deadline
instead of iteration count. Each iteration can skip a month, so
the old `capMinutes + 10_000` cap let `0 0 30 2 *` walk ~200 000
years before bailing; the new path returns null in microseconds.
- `oneShotJitteredNextCronRunMs` returns `idealMs` (not `createdAt`)
when the pulled-forward time would precede `createdAt`. The old
clamp made an 08:59:30-scheduled `0 9 * * *` fire on the very next
tick — ~29 s before ideal — instead of at 09:00.
## CronList + CronCreate output
- CronList output adds a `prompt:` row, JSON-encoded so newlines
stay on one line, truncated to ~200 UTF-8 bytes on a char
boundary. The model can recall a task's intent after compaction
and use it as the source for the documented refresh ritual.
- CronCreate normalizes `args.cron` whitespace BEFORE
`parseCronExpression` so `parsed.raw` is single-line. Otherwise
inputs like `"1\n2\n3\n4\n5"` (legal — parser accepts any \s+)
produced a multi-line `humanSchedule:` row via the cronToHuman
raw-fallback branch.
## Misc hardening
- `KIMI_CRON_CLOCK=file:<path>` reads at most 64 bytes via
`openSync` + `readSync` so a stray-large file can't OOM.
- SIGUSR1 handler logs swallowed `tick()` exceptions to stderr when
`KIMI_CRON_DEBUG=1` (matches scheduler's debug pattern); silent in
production.
- Documentation rewrite across cron-list.md / cron-create.md /
cron-delete.md so the documented stale + nextFireAt behaviour
matches the implementation (recurring stale tasks auto-delete after
the final fire; `nextFireAt` is an ISO timestamp; refresh ritual
is "just CronCreate again — the old id is already gone").
Tests cover each of the above. Suite at 2090+ passing across
agent-core, kosong, and the kimi-code app; typecheck clean across
all workspace packages.
* feat(cron): persist scheduled tasks across kimi resume
Add per-id JSON persistence so cron tasks survive a kimi resume of the same session.
Core changes:
- CronManager: addTask / removeTasks mirror mutations to <sessionDir>/cron/<id>.json
- CronManager.loadFromDisk() rehydrates the in-memory store on resume
- CronManager.flushPersist() drains pending writes for graceful shutdown
- SessionCronStore.adopt() inserts persisted tasks with original id and createdAt
- Extract shared createPerIdJsonStore utility from background/persist.ts
- Refactor background/persist.ts to use createPerIdJsonStore (no behavior change)
- New tests: resume.test.ts, persist.test.ts, per-id-json-store.test.ts
- Update cron-create / cron-list / cron-delete docs to reflect session lifetime
* fix(agent-core): fix cron-stop-on-close test import for tsgo compat
* feat(cron): persist lastFiredAt cursor and scope approval rules
- persist lastFiredAt across resume so recurring tasks don't replay
- add one-shot pinned-date guard to reject >1-year-out first fires
- scope CronCreate approvalRule to exact payload (cron, prompt, recurring)
- add resume replay tests and corrupt-cursor fallback test
- stop cron before awaiting background shutdown so due ticks cannot
start a fresh turn while session.close() is mid-flight
- filter cron_job / cron_missed origins from markdown export so the
internal <cron-fire ...> envelope no longer leaks into user-facing
exports
Render a clickable OSC 8 hyperlink pointing to the release notes page
in the update available prompt, so users can easily review changes
before deciding to install.
* fix(migration): map default_yolo to default_permission_mode instead of dead yolo field
The kimi-cli config key `default_yolo` was being migrated to `yolo` in
kimi-code config.toml, but `yolo` is a dead field that no code reads.
The real config key for yolo mode is `default_permission_mode = "yolo"`.
* chore: add changeset for migration yolo mapping fix
* 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
