kimi-code/packages/klient
7Sageer 6be26978b1
feat: auto-generate session titles via the managed chat_title tool (#2351)
* feat: auto-generate session titles via the managed chat_title tool

With the auto-title experimental flag on and a managed OAuth login, the
session title is generated from the first prompt, replacing the
truncated-prompt easy title. A custom title set by the user is never
overwritten, and generation failures degrade silently to the easy title.

- oauth: fetchChatTitle for the platform /tools chat_title method
- agent-core (v1): fire-and-forget generation on the first prompt
- agent-core-v2: sessionTitle domain watching the easy-title event
- kap-server: POST /sessions/{id}/title/generate for manual regeneration

* fix: harden auto-generated session titles

* fix: preserve managed title request headers

* Pair auto-title endpoint overrides with matching OAuth credentials

* fix: preserve legacy custom session titles

* fix: preserve automatic session title invariants

* refactor: keep only the on-demand session title generation interface

Drop the automatic wiring on both engines: the v1 (TUI) first-prompt
trigger and the v2 easy-title event watcher. SessionTitleService's
generateTitle() stays as the single on-demand entry point behind the
auto-title flag, backing the kap-server title/generate route. The
changeset goes away too: with no shipped consumer, the remaining
surface is not user-perceivable.

* feat: generate session title from the first recorded prompts

Record up to three sanitized natural-language prompts in session
metadata (skill / plugin activations excluded) and compose the
chat_title input as order-labeled lines truncated to a 1000-char
budget, falling back to lastPrompt for sessions without recorded
prompts.

* test: make session title race tests deterministic

* Generate session titles from agent conversation history

* fix: reject title generation without user prompts

* fix: bound session title prompt history

* feat: enable session title generation without an experimental flag

* test: cover session title generation through the public REST path

* feat: request session title generation from the TUI after each turn

* Retry auto title generation for prompt-derived session titles

* feat: record session title source and harden the generation lifecycle

- persist titleSource (prompt/generated/custom); skip auto-generation over
  an already-generated title unless forced, and never over a custom one
- plumb the force option from the core through klient and node-sdk to the
  REST title/generate endpoint
- drop the title write-back when the session scope was superseded
  mid-flight, and retry once with a force-refreshed token on a 401
- stop closing sessions a concurrent public resume has handed out in the
  temporary resume paths (generateSessionTitle, renameSession)
- accept session.meta.updated patches without lastPrompt in klient event
  validation, and emit exactly one metadata event per applied title
- remove the retired prompts field heal and drop the changeset (the
  behavior is only perceivable on the experimental v2 engine)

* chore: follow agent-core comment convention

* fix: ignore stale session title callbacks

* fix: preserve session title state invariants

* refactor: seed session lifetime instead of querying the workspace handler

The session title service must not depend on the Workspace-tier handler
registry. The handler now seeds each session scope with an abort signal,
fires it synchronously when a close begins, and the title service carries
the signal on its request, drops the write-back once aborted, and drains
an in-flight generation through the onWillCloseSession hook.

* fix: honor the legacy custom title marker over a stale titleKind

A v1 rename spreads the original state.json document, so an explicit
isCustomTitle: true can travel with a stale titleKind. The explicit
marker now wins on load, and every persist double-writes the derived
isCustomTitle so released v1 builds keep recognizing the custom title.

* fix: serialize session access and expose the session title state

The temporary resume/rename/close paths and the public lifecycle
operations now share a per-session queue, so a public resume can never
receive a handle whose cleanup close is already in flight. Session
summaries carry the canonical title state, letting the TUI skip title
generation for sessions whose title was already generated or customized
instead of re-asking after every turn.

* chore: add session title changesets

* fix: close the session lifecycle races around close and title generation

A close/archive is now tracked in a closing registry from its first
synchronous step until disposal: get/list hide the closing session and
resume waits the close out instead of returning the doomed handle, and
fork waits out an in-flight source close. The title service tracks the
whole generateTitle call as the unit the close hook drains, and the
generated-title write re-checks the lifetime signal inside the serialized
metadata update so an abort landing while the update is queued still
vetoes the write-back.

* feat: project the session title state through the session index

readSummary and the read-model mirror carry titleKind, so listSessions
reports the same canonical title state as a resumed session's summary.

* fix: serialize the remaining session access paths in the SDK

forkSession and explicit-id createSession join the per-session queue, and
the harness resume fast path skips a session whose close is in flight
instead of returning the closing facade (which then failed every call
with session.closed); its late onClose no longer evicts the fresh
session either. The harness rename event now carries isCustomTitle so
the TUI stops asking for a generated title after a local rename.

* fix: detach the external abort listener once the chat title request settles

* fix: harden the session close/archive and create/fork lifecycle

The closing registry now records the operation kind: an archive arriving
during a plain close waits it out and lands the archived flag on the
persisted document instead of riding the close to success, and a failing
close hook no longer strands a half-closed session — the teardown always
completes while the hook error still reaches the caller. create and fork
reserve their target id synchronously with the existence check, so a
concurrent create/fork of the same id loses up front and can never tear
down the winner's scope or directory.

* fix: keep forced title regeneration independent and veto queued title writes atomically

Plain generateTitle calls still coalesce onto one shared in-flight
generation, but a forced regeneration always runs on its own so it is
neither swallowed by a plain call's early exit nor shares its result; the
close hook drains every active generation. The allowWhen veto now runs
inside applyUpdate with no await between the check and the mutation, so
an abort cannot slip into the gap.

* fix: carry the title state through the session index and klient contract

The klient session summary schema no longer strips titleKind, and the
index readSummary honors a legacy isCustomTitle marker over a stale
titleKind, so listSessions reports the same canonical title state as a
resumed session.

* fix: coalesce harness resumes, lock fork targets, and cover the title state end to end

Concurrent public resumeSession calls now share one in-flight resume and
one facade instead of building parallel facades over the same engine
handle (a close on either would strand the other). forkSession takes the
source and target queues in sorted order, so fork(A->X) is atomic against
create(X) and fork(B->X) without an ABBA deadlock. The emitMetaUpdated
patch type drops the redundant undefined union, and the SDK tests now
cover facade coalescing and the title state across list and resume.

* fix: serve the canonical title state from the session index and version the read-model cache

readSummary now derives the title state with the same priority chain as
the metadata document's canonical normalization (explicit custom marker,
valid titleKind, legacy false marker, customTitle, plain title), so list
and resume agree on legacy documents too. Read-model cache entries carry
a summary version stamp and older-stamped entries are treated as cold
misses, so an upgraded reader never serves a stale-shaped summary.

* fix: let the newest title generation request win the write-back

A forced regeneration could be followed on disk by an earlier plain
call's slower backend response. Each generation now carries a
monotonically increasing sequence (assigned only once a request actually
proceeds to generation), and the serialized metadata write is vetoed
unless the writer is still the newest request.

* fix: fold archive into close and own the create/fork rollback

An archive requested during a plain close is applied through the live
metadata during the teardown (or lands on the persisted document when it
arrives too late or the close fails), publishes the archived event, and
works on cold sessions too. A resume waiting on a failed close retries
instead of propagating the hook error, the teardown completes even when
the agent drain fails, and the create/fork rollback only ever removes
its own handle — a loser of the reservation race can no longer tear down
the winner's live scope.

* fix: key harness resume coalescing by the full input

Concurrent resumes only share a facade when their inputs match — a
caller passing different dirs, replay, profile, or kaos options gets its
own resume instead of having its options silently dropped.

* refactor(agent-core-v2): drop session close-awareness from title generation

Auto title is best-effort: a generation racing session close no longer
cancels its fetch or guards its write-back, so the per-session
sessionLifetime AbortSignal seed, the onWillCloseSession drain, and the
close-time invalidation go away. The newest-request-wins write-back
predicate stays.

* Delete .changeset/sdk-session-title-kind.md

Signed-off-by: 7Sageer <sag77r@hotmail.com>

* refactor(session-title): drop the unused force regeneration path

Nothing calls force: with it gone, plain calls always coalesce onto the
shared in-flight generation, so the generation sequence and the
caller-supplied allowWhen veto lose their only purpose and go with it.
The title/generate REST route takes no body anymore.

* refactor(agent-core-v2): drop the title state projection from the session index

The listed-session titleKind had no consumer: the TUI's title-generation
gate seeds from the resumed summary, which reads the live metadata
document, and the kap-server REST wire never carried the field. Removing
the projection also retires the read-model summary version stamp (the
remaining shape is fully field-checkable) and the duplicate title-kind
derivation that had to stay in lockstep with sessionMetadata. The klient
list contract and the node-sdk list mapper drop the field with it; the
resumed/live summary still reports the canonical title state.

* refactor(agent-core-v2): inline the transcript live-tail merge into messageLegacy

mergeContextTranscriptWithLive had a single caller; move the logic into
messageLegacyService as the private mergeLiveTail and drop the export.

* refactor(agent-core-v2): drop the closing registry from the session lifecycle

Auto title no longer consumes close-awareness, so the machinery goes
back to the simple forms: close/archive run straight through, resume
no longer waits out an in-flight close, create/fork drop their target
reservation, and a cold archive is a no-op again. Reverts the behavior
of e7c397a7c and cd1cea0fd on top of the sessionLifecycle rename.

* fix(agent-core-v2): complete the HostRequestHeaders migration in the title test

The main merge reduced #/kosong/model/hostRequestHeaders to the pure
port contract; define the test's headers as a plain value matching it
and tidy the SDK test import grouping.

* fix(node-sdk): mark resume telemetry field ignored

* feat(tui): request the session title as soon as a prompt is accepted

* fix(agent-core-v2): drop the numbered user prefixes from the title request input

* refactor(tui): ask for the session title only once per session attach

* refactor(tui): drop the automatic session title trigger

Keep the capability only: the engine-side title generation service, the
POST /sessions/{id}/title/generate route, and the SDK generateSessionTitle
method stay; the TUI no longer requests a title on prompt accept or on
session attach. The changeset now covers the SDK capability instead of a
CLI-facing auto title.

* Delete .changeset/session-title-generation.md

Signed-off-by: 7Sageer <sag77r@hotmail.com>

* feat(agent-core-v2): add forced session title regeneration

ISessionTitleService.generateTitle and the metadata write-back take an
optional force flag that bypasses the custom/generated guards, so an
explicit user request (the desktop/web rename field's Gen Title action)
can overwrite any current title; the applied title is marked generated.
Forced calls skip the in-flight coalescing, and a forced write is plain
last-writer-wins.

kap-server's POST /sessions/{id}/title/generate accepts an optional
{ "force": true } body; klient and the node-sdk plumb the option through
(GenerateSessionTitleInput.force).

Also renumber SESSION_TITLE_UNAVAILABLE to 40923: main assigned 40922 to
PAGE_TOKEN_MISMATCH after this branch forked.

* feat(agent-core-v2): selectable conversation excerpts for title generation

generateTitle gains a source option alongside force:

- user_prompts (default): the existing first-prompts window, unchanged.
- first_turn: the opening user prompt paired with the first turn's final
  assistant text — strict, so a caller asking before the first reply lands
  simply gets unavailable and can retry at the next turn boundary.
- digest: first prompt + latest prompt + the latest turn's final assistant
  text, tolerating a compacted window by using whatever segments survive;
  meant for explicit regeneration on multi-turn sessions.

Assistant segments keep only natural-language text parts (tool calls,
thinking, and media never contribute) and pass through the shared metadata
sanitizer, which redacts secrets and long base64-looking runs; each
segment is capped (user 300, assistant 600/400) so the composed
chat_content stays within the 1000-char budget. The kap-server route,
klient contract, and node-sdk plumb the option through. Excerpt extraction
is covered against the real context memory (loop-event folding), and the
REST surface gains a digest composition case.

* feat(agent-core-v2): gate session title generation behind an experimental flag

Registers the  flag (off by default; env
KIMI_CODE_EXPERIMENTAL_SESSION_TITLE, the master flag, or the
[experimental] config section) and makes generateTitle report
unavailable while it is off, so every entry point — the kap-server
route, klient, node-sdk, and through them the clients' auto trigger and
rename-field action — is inert unless the user opts in.

* refactor(agent-core-v2): rename the title flag to auto_session_title

Snake-case id matching search_worker / persistence_minidb_readmodel; env
KIMI_CODE_EXPERIMENTAL_AUTO_SESSION_TITLE.

* fix(agent-core-v2): land the merge resolution leftovers

The main-merge commit captured pre-fix snapshots of four files; the
actual resolutions only lived in my working tree: the LifecycleScope
import move to #/app/scopes, the titleKind port of
applyPromptMetadataUpdate, the Promise<void> pinning of the metadata
update queue, and the reloadSession runSessionAccess closure.

* test(node-sdk): enable the auto_session_title flag in the title suites

Generation now reports unavailable with the flag off, so the two
title-generation harnesses opt in through the written config's
[experimental] section.

* chore: changeset for the experimental web session titles

* chore: scope the title changeset to the SDK package

* chore: cover the internal packages in the title changesets

---------

Signed-off-by: 7Sageer <sag77r@hotmail.com>
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
2026-08-13 17:59:57 +08:00
..
examples feat: unify the host identity across OAuth, telemetry, and kap-server (#2382) 2026-07-30 13:45:41 +08:00
scripts feat(klient): contract-driven facade with http/ipc/memory transports (#1768) 2026-07-16 16:43:09 +08:00
src feat: auto-generate session titles via the managed chat_title tool (#2351) 2026-08-13 17:59:57 +08:00
test feat: auto-generate session titles via the managed chat_title tool (#2351) 2026-08-13 17:59:57 +08:00
AGENTS.md refactor(agent-core-v2): rebuild the model wire layer on the kosong architecture (#1970) 2026-07-21 13:03:54 +08:00
CHANGELOG.md ci: release packages (#2342) 2026-07-30 14:56:30 +08:00
Dockerfile feat(klient): contract-driven facade with http/ipc/memory transports (#1768) 2026-07-16 16:43:09 +08:00
package.json ci: release packages (#2342) 2026-07-30 14:56:30 +08:00
README.md feat: agent-core-v2 permission/workspace refactors and transcript durability (#2021) 2026-07-22 19:21:56 +08:00
tsconfig.examples.json test(klient): add real-server smoke coverage (#1713) 2026-07-15 15:24:36 +08:00
tsconfig.json feat(klient): contract-driven facade with http/ipc/memory transports (#1768) 2026-07-16 16:43:09 +08:00
tsdown.config.ts feat(transcript): add unified transcript layer, drop the /api/v2 RPC surface (#1888) 2026-07-20 15:33:05 +08:00
vitest.config.ts feat(klient): contract-driven facade with http/ipc/memory transports (#1768) 2026-07-16 16:43:09 +08:00

@moonshot-ai/klient

Contract-driven client SDK for the agent-core-v2 engine. One facade, two transports — you pick the transport once at creation; everything after that is byte-identical:

import { bootstrap, logSeed, resolveLoggingConfig } from '@moonshot-ai/agent-core-v2';
import { createKlient } from '@moonshot-ai/klient/memory';   // or '/ipc'

const { app } = bootstrap({ homeDir }, [
  ...logSeed(resolveLoggingConfig({ homeDir, env: process.env })),
]);
const klient = createKlient({ scope: app });

const env = await klient.global.env();
const sessions = await klient.global.sessions.list({ limit: 20 });

const session = await klient.global.sessions.create({ workDir: process.cwd() });
const agent = klient.session(session.id).agent('main');
agent.events.on('assistant.delta', (e) => process.stdout.write(e.delta));
agent.events.on('prompt.completed', () => console.log('\ndone'));
await agent.prompt({ input: [{ type: 'text', text: 'Say OK.' }] });

await klient.close();

Architecture

facade (klient.global.*, klient.session(id).*, session.agent(id).*, *.events.*)
   ↓ single-object params, zod-validated
contract (procedure schemas, shared by all transports)
   ↓
KlientChannel { call, listen }   ← the only transport SPI
   ↓
ipc │ memory
  • Facade — aggregated methods, no engine service tokens, no onDid*/onWill* event names. There is no escape hatch to raw services: the facade is the public contract.
    • klient.global.*sessions.* (incl. create), workspaces.*, config.*, providers.*, models.*, catalog.*, auth.*, flags.*, plugins.*, hostFs.*, env().
    • klient.session(id).*get/setTitle/update/status/close/archive/ restore/fork/createChild, approvals.*, questions.*, interactions.*, agents().
    • session.agent(id).*prompt/steer/cancel/runShellCommand/ cancelShellCommand/getModel/setModel/setPermission/getUsage/getContext/ getPlan*/getTasks*/stopTask/getTaskOutput.
  • Contract — every method has a zod input tuple + output schema, validated on the client before send / after receive (default on; validate: false to disable). Validation is sub-µs for typical payloads — cheaper than the JSON serialization the wire already pays.
  • Eventsklient.events.on(...) for the global bus (config.changed, kosong.models.changed, session.archived, …), session(id).events.on('metadata.changed' | 'interactions.changed' | 'interactions.resolved'), and agent(id).events.on('turn.started' | 'assistant.delta' | 'tool.call.started' | 'prompt.completed' | …). Underlying subscriptions are shared and ref-counted; payloads are validated; bad payloads drop to events.onError.

Transports

entry options events
@moonshot-ai/klient/ipc { socketPath, token? } same socket
@moonshot-ai/klient/memory { scope } (a bootstrapped engine app scope) direct emitter/bus subscription

ipc and memory share one in-process dispatcher, so they behave identically by construction; memory additionally JSON round-trips every value so results cross the same JSON boundary a socket transport would impose. The IPC host ships with the transport: serveKlientIpc({ scope, socketPath }).

The same conformance suite runs against both transports in this package's tests (test/helpers/conformance.ts — one test file per transport).

This package also hosts the e2e suites (the retired server-e2e package was folded in here):

  • test/e2e/legacy/ + test/e2e/harness/ — the legacy /api/v1 live suites and their client harness (skip unless KIMI_SERVER_URL is set; the v1 surface has no in-memory equivalent, so these stay live-server-only).

The docker e2e runner (pnpm docker:e2e) runs this whole vitest suite inside a container against a container-local server. See AGENTS.md for the testing rules.

Scope

The facade covers the global (app), session, and agent surfaces shown above. What it deliberately leaves out (for now): onWill/hook-style interception (engine hooks are in-process OrderedHookSlots and not wire-exposable), file upload (v1 multipart REST only), and the terminal surface (v1 REST + WS only).

Smoke check

pnpm -C packages/klient smoke

examples/smoke.ts boots an in-process engine (memory transport) and asserts the global facade end-to-end — no server needed. examples/basic.ts is a shorter narrated tour; examples/context-usage.ts traces context-size readings through a real prompt (requires KIMI_EXAMPLE_MODEL + KIMI_EXAMPLE_API_KEY).