131 commits

Author	SHA1	Message	Date
Luyu Cheng	d6021fa036	feat(kap-server): accept bundled skill activations on the prompt submission route (#2982) ... * feat(kap-server): accept bundled skill activations on the prompt submission route The bundled-submission capability was only reachable through the in-process klient transports; the App talks to kap-server over /api/v1. The submit-prompt route now accepts an optional non-empty skills field and delegates to IAgentSkillService.promptWithSkills — same validation, events, and single bundled user message as the TUI path — skipping its own prompt-metadata update (the engine owns it there) and mapping skill.not_found / skill.type_unsupported onto the skills route's codes. To return the submission's queue identity, the engine's promptWithSkills now resolves with prompt_id / user_message_id / created_at / state (plus turn_id once launched), mirrored through the klient contract. * refactor(agent-core-v2): slim the promptWithSkills result contract Drop the user_message_id field (it is always the same identity as prompt_id — the route duplicates it) and narrow state to the running/queued/blocked vocabulary, mapped at the engine edge instead of exposing the internal seven-state PromptState on the wire. * fix(kap-server): harden bundled skill submissions against review findings - Validate bundled skill names and types before any media materialization or control override, so a rejected bundle leaves session state untouched (the engine still re-validates authoritatively). - Declare the 40415/40912 outcomes on the submit route so the generated API documentation includes them. - The klient output schema no longer tolerates a missing promptWithSkills result (a transport-level absence now raises instead of resolving undefined), and a failed launch surfaces as an error rather than a successful running result. - Add the changeset for the new public API field. * fix(kap-server): preflight bundled skills before agent materialization and stabilize listed content - Skill preflight now runs on the session's catalog before the main agent is resolved, so a rejected bundle cannot mutate session metadata by registering main (regression test on a cold session without an agent). - The prompts list projection strips the stored skill blocks from a bundled prompt, so GET /prompts returns the same caller-only content as the submit response. * fix(kap-server): reject bundled prompt_id combos at preflight and clean queued staging - The skills + prompt_id incompatibility rejection now runs at the initial bundled preflight, before the main agent is materialized or any override binds (previously a yolo override could bind before the 40001). - Queued bundles no longer skip staging cleanup forever: the discard is deferred to the bundle's prompt.completed / prompt.aborted lifecycle event, mirroring the plain path's launch-raced cleanup. * fix(kap-server): clean queued bundle staging on the steer path too A queued bundle steered into the active turn is consumed at steer time, but the engine publishes prompt.completed/aborted only for the parent — the deferred cleanup never fired and its subscription leaked. The prompt.steered event (matching promptIds) now counts as the child's intake-completion signal. * fix(agent-core-v2): materialize daemon-ref media on the steer and inject paths startNext materializes daemon file references into the session media store before a prompt's turn, but steer() and inject() enqueued the same references without that intake, leaving the staging upload as the only copy — any staging cleanup at steer time would delete the media the turn is about to consume. Both paths now run the same intake before the SteerStepRequest is created, so prompt.steered is a truthful intake-complete signal. * fix(kap-server): defer staging cleanup to turn settlement, never to steer time Prompt-intake materialization is best-effort: when it degrades, the daemon upload is the request-time resolver's fallback source. Discarding staging at prompt.steered could therefore delete the only readable copy before the parent's request ran. Cleanup is now uniformly event-driven — the bundle's own prompt.completed/aborted, or the steer parent's — so the upload always outlives the request it feeds. * fix(kap-server): install settlement tracking before bundled enqueue A hook-blocked bundle completes synchronously inside the submission call, and an exceptionally fast launch can settle just as early — a post-call subscription misses the only settlement event and leaks both the staging blob and the listener. The tracker now subscribes before enqueueing, buffers lifecycle events, and settles against the returned prompt id (or its steer parent's). * fix(kap-server): scope settlement tracking to the owning agent and dispose on rejection - The tracker now subscribes through the agent-scoped IEventBus instead of the App-scoped IEventService: prompt lifecycle events from other sessions never reach it, so a colliding client-chosen prompt id cannot trigger a foreign settlement (and the steer re-target only follows this agent's parent). - A bundled submission that rejects after the tracker was installed now disposes it on the error path instead of leaking a permanent listener. * fix(agent-core-v2): keep steered prompts queued until their media intake finishes Materializing a steered prompt's daemon-ref media awaits a file copy during which the active turn may finish. Records are now spliced out of the queue only after that copy completes, and when the turn is gone by enqueue time they are restored to pending so startNext can launch them as fresh prompts — their handles always launch or settle. * fix(agent-core-v2): revalidate the queue and active turn after steer media intake The daemon-ref copy yields, so settle/abort can consume selected records and the active turn can rotate meanwhile. Only records still pending are steered, and only into the turn that was active at entry; records that vanish from the queue are left to their own launch path, and a missing turn restores them to pending instead of splicing an unrelated tail prompt. The intake/queue-preservation contract is documented in the module header. * fix(agent-core-v2): steer only the surviving records and keep their media truthful - The steered content is rebuilt from the records that are still pending after the media intake, so an aborted or concurrently consumed record's text is never injected (or injected twice) alongside the surviving handles. - The enqueue is wrapped so an activeTurnOnly rejection restores the records to pending (the loop throws instead of resolving a missing turn, which made the previous rollback unreachable). - The merged origin now carries the union of every record's bundled skillActivations, and prompt.steered publishes the caller-only content, so the skill instructions reach the model with their metadata intact while the event projection stops leaking internal skill markdown. * fix(agent-core-v2): harden steer rollback and register bundled prompt ids * fix(agent-core-v2): strip bundled blocks from prompt.queued and reject partial steers * fix(kap-server): update session metadata for bundled prompts routed to subagents * fix(agent-core-v2): restart queue after raced steer rollback and prefix skill blocks in merged steer * fix(agent-core-v2): block queue advancement during steer admission * chore: drop the changeset for server-only protocol plumbing	2026-08-18 14:57:13 +08:00
liruifengv	eaa3969dd3	feat(kap-server): add page mode, updated_before, and batch archive/restore to v2 sessions (#2983) ... * feat(kap-server): add page-number mode and total to GET /api/v2/sessions The v2 session list gains a stateless 1-based `page` parameter beside the opaque page_token cursor for admin-style lists that jump arbitrarily: each request stays a full independent snapshot, no token is minted, and `page` + `page_token` together fail 40001. Every response now carries `total` (the filtered/sorted set size) in both pagination modes. * feat(kap-server): add meta.updated_before filter to GET /api/v2/sessions Symmetric with meta.updated_after (inclusive boundary, Unix ms), applied at the edge over the drained set and bound into the page_token query fingerprint like every other condition. * feat(kap-server): add POST /api/v2/sessions:archive and :restore batch endpoints Batch archive/restore for session-management views: { ids } (non-empty, ≤5000 unique after dedup) answers per-item results in input order with succeeded/failed counts — only a body validation failure fails the whole request, and an unknown id folds into its own item as 40401. The live/cold split keeps the batch cheap: a session with a live handle goes through the full ISessionLifecycleService chain (agents drain, scope teardown, mirror drain), while a cold session is never materialized — the new setColdSessionArchived helper in agent-core-v2 patches the persisted state.json (archived/archivedAt, updatedAt preserved, mirroring setArchived's touchUpdatedAt: false semantics), mirrors the flipped summary into the read-model queue, and republishes the same event.session.archived bus event the live lifecycle emits (:restore publishes nothing, matching the live restore). Hot items run with bounded concurrency and the batch ends with one shared ISessionIndexMirror.drain(). * docs(server-api): document v2 sessions page mode, total, updated_before, and batch archive/restore * fix(kap-server): deep-import workspace lifecycle symbols in the v2 sessions route CI's tsgo/rolldown (Linux) fail to bind liveHandlerForSession and IWorkspaceLifecycleService through the agent-core-v2 package-root barrel even though it re-exports them; the same files use the established deep-import pattern already used for the git domain. * fix(kap-server): inline the live-handler lookup in the batch route The previous deep imports still fail to resolve on CI's Linux toolchain (tsgo TS2307, rolldown MISSING_EXPORT) while every other module path from the same package binds fine. Keep the route self-contained: the hot-path lookup is a five-line loop over IWorkspaceLifecycleService's handlers (mirrors agent-core-v2's liveHandlerForSession), and the tests assert non-materialization behaviorally via the live map instead of importing the same two symbols for spies. * fix(kap-server): drive the batch hot path through getLiveSessionById The phantom only hits the workspaceLifecycle-group symbols in these two files on CI's Linux toolchain; getLiveSessionById is observed to bind fine there. It returns the session's live scope directly (no resume), which is exactly what the batch hot path needs. * refactor(kap-server): move the batch live/cold split into agent-core-v2 setSessionArchivedBatch owns the split next to the cold patch: live sessions go through the full lifecycle chain via the workspace handler accessor (the v1-proven resolution path), cold sessions through the direct write. The route becomes a thin wire-code adapter, and the batch tests assert the live chain behaviorally (disposal, events, index) instead of spying through scope accessors. * fix(agent-core-v2): import sessionLookup relatively from coldSessionArchive The '#/app/workspaceLifecycle/*' specifier resolves from src/ and src/app/* files on CI's Linux toolchain but not from src/workspace/sessionLifecycle/ (tsgo TS2307, rolldown follows); a relative import bypasses the package-imports mapping. * fix(agent-core-v2): migrate the batch hot path to ISessionManager Main's workspace/session DI refactor removed the workspaceLifecycle lookup modules; the live branch now goes through the App-level ISessionManager (the same entry the v1 action route uses post-refactor) with getLiveSessionById from the new sessionManager lookup. * feat(kap-server): add the id,archived item projection to GET /api/v2/sessions fields=id,archived trims each item to { id, archived } for select-all-matching flows (the session admin page's Gmail-style select-all). Only that projection gets the relaxed page_size ceiling (10000); unknown fields, non-pair subsets, and include=git combinations are 40001, and the projection binds into the page_token fingerprint so shapes never flip mid-pagination. * fix(agent-core-v2): serialize the batch cold write against in-flight resumes Codex review on #2983: while a resume is in flight the live registry hides the handle, so the batch route could classify the session as cold and its direct write would race the materializing metadata service (its stale in-memory document wins the next write, silently un-archiving the session after the endpoint reported success). The batch now settles the resume first: SessionManager registers the whole resume promise synchronously at the App level (controllerForSession is async, so the controller's own resuming map learns about it a few microtasks late) and whenResumeSettled awaits it before classification — a settled resume lands the item on the live chain, a failed one falls back to the cold path. Also folds the module header down to the package's external-role comment convention. * fix(agent-core-v2): publish SessionArchived as an Event2 class in cold archive * fix(agent-core-v2): serialize batch archive/restore with session lifecycle transitions * fix(agent-core-v2): serialize session delete with the lifecycle chain * fix(agent-core-v2): mirror the persisted metadata on cold archive, not the index summary * docs(agent-core-v2): bring sessionManager comments and new tests to package conventions * fix(agent-core-v2): normalize legacy session metadata before the cold archive write * fix(kap-server): serialize the v1 single-session archive with the lifecycle chain * chore: drop changesets for internal-only protocol work * fix(agent-core-v2): encode cold-archived metadata for v1 readers * fix(agent-core-v2): serialize fork and createChild with the source session's chain * refactor(agent-core-v2): chain every session lifecycle method and hand batch sections unguarded ops * fix(agent-core-v2): propagate failed resumes to the next settle * fix(agent-core-v2): roll back the unannounced handle when a resume fails mid-materialization * fix(agent-core-v2): read and migrate the legacy session-meta location on cold archive * fix(agent-core-v2): serialize explicit-id session creation with the lifecycle chain create() with a caller-supplied sessionId bypassed the per-session chain, so a concurrent batch archive could classify the half-created session as cold and write archived state that the live metadata service later overwrites. Creation now queues on the target id's chain whenever an explicit id is present. Also type the resume-failure maps as Error and normalize at the catch site, satisfying only-throw-error. * style(kap-server): strip comments from the session routes per the no-comments convention * fix(agent-core-v2): serialize explicit fork and child target ids on the lifecycle chain fork() and createChild() with a newSessionId locked only the source id, so a batch archive of the target could slip into the creation window: the index already knows the half-created session, the batch writes archived state to its document, and the fork's in-memory metadata later overwrites it. Both operations now acquire the deduped, sorted key set so multi-key sections always take locks in one deterministic order.	2026-08-18 13:57:37 +08:00
Haozhe	5ae82cd5bc	feat(agent-core-v2): disable the tower feature entirely (#3023)	2026-08-18 13:38:13 +08:00
Haozhe	8267bb8fce	feat(kap-server): add workspace fs:suggest file completion endpoint (#3019)	2026-08-18 11:53:48 +08:00
Haozhe	3ded08084a	fix(protocol): expose turn ended event time (#3011) ... * fix(protocol): expose turn ended event time * fix(protocol): expose turn ended event time * chore(changeset): remove patch release entry * test(node-sdk): align background task parity expectations	2026-08-18 10:16:12 +08:00
Haozhe	1ab19190e9	refactor(agent-core-v2): strip comments from agent-core-v2, kap-server, and transcript (#3010)	2026-08-18 00:30:49 +08:00
bj456736	09976b0914	feat(cli): add --web-title and expose it via /meta (#2989) ... * feat(cli): add --web-title and expose it via /meta * refactor(kap-server): pass optional web_title directly in /meta Per the repo rule for optional object properties, pass undefined directly instead of a conditional spread; serialization omits the unset value. * fix(cli): sync web bundle with instance tab title support The committed dist-web bundle predates the document title feature, so a released `kimi web --web-title` served a client that never read web_title. Rebuilt from code-app (feat/web-document-title) via sync:web; the bundle now titles tabs from web_title or the active workspace directory. * ci: retrigger checks after flaky harness cleanup failure --------- Co-authored-by: wbxl2000 <wbxl2000@outlook.com> Co-authored-by: bj456736 <bj456736@users.noreply.github.com>	2026-08-17 20:19:15 +08:00
Haozhe	2265305e81	refactor(agent-core-v2): replace defineOp/Model with Event2 dispatch and replayable states (#2909) ... * refactor(agent-core-v2): replace defineOp/Model with Event2 dispatch and replayable states - replace defineOp/Op/OpDescriptor/toEvent and defineModel/defineCheckpointedModel with Event2 subclasses: durable classes declare static durable + schema, serialize() keeps the wire record shape byte-frozen, transient classes stay off the journal - define states via defineState(...).replayable(...).on(Event2, fold): immer produceWithPatches folds with atomic prepare/commit, .undoable() trait drives prompt-submit checkpoints and context.undo, ephemeral kv keys keep imperative set - degrade IWireService to a journal adapter; the agent event dispatcher owns the pipeline (fold -> set -> appendRecord -> publish) and silent restore - align downstream event surfaces: kap-server WS envelope timestamp from event.time, klient event schemas gain time, node-sdk/acp-server/print wiring updated - rewrite gen-wire-manifest/gen-state-manifest for the unified registry and replace the op-uniqueness lint with event-uniqueness * fix(ci): repair Event2 prompt and media projections - restore prompt admission and session media materialization - align transcript, WS, SDK, and replayable media state projections - update affected tests and generated state manifest * fix(ci): update prompt event and projection expectations - update snapshots for the durable prompt.accepted event - normalize prompt.steered media in transcript projections	2026-08-17 17:38:50 +08:00
7Sageer	d833a1a893	feat: engine-native image references via kimi-file:// media resolver (#2593) ... * feat: engine-native image references via kimi-file:// media resolver * fix(agent-core-v2): regenerate state manifest for media resolver rename * feat(agent-core-v2): add audio MediaKind and tag/ref fold helpers to media ref contract * fix(agent-core-v2): synthesize image path tag when degrading bare file references * fix(agent-core-v2): scrub dangling alias re-exports in contract type generator * feat(transcript): project paired media tag+ref as single attachments in read models * fix(kimi-code): fall back to inline image when cache write fails after upload * fix(agent-core-v2): pair media path tags with refs by adjacency and path, keep unpaired tags * fix(kap-server): fold media tag+ref pairs out of prompt snapshot projection * fix(kap-server): list attachment-only prompts as empty user messages * fix(kap-server): keep live attachment ids across transcript overlay and heal * fix(kap-server): keep promptAttachments off the legacy session event wire * fix(kap-server): inherit the backfilled turn header on mid-turn terminal projection A projector that attached after turn.started built the terminal turn.upsert with an empty header, and the whole-header replace downstream wiped the backfilled origin / prompt / attachmentIds — only the debounced best-effort heal could restore them. Fall back to the producer store's seeded header (via a new optional ProjectorLookups.turn) when currentTurn misses, and cover the mid-turn attach path with a service-level regression test. * refactor(agent-core-v2): move media ref contract out of kosong into agent/media The kimi-file:// daemon reference grammar, media path tags, and the tag/ref fold are engine-internal conventions, not provider-wire contract; keep src/kosong untouched. Root exports and SDK re-exports are unchanged. * feat(agent-core-v2): materialize prompt media into the session media dir Pasted and uploaded media now materialize under the session's own media/ dir instead of the shared cache, so the copies follow the session's lifecycle: fork carries them along, session deletion cleans them up. A new Session-scope ISessionMediaStore owns the dir: atomic tmp+rename materialization with a unified extension policy, and canonical-vs-hint display-path resolution. The persisted ?path= is a write-time snapshot — readers prefer the session-canonical location, so fork and home relocation never hand the model a dead path. Prompt intake normalizes every daemon reference through the single enqueue funnel (REST edge, SDK prompt/steer, gateway), serialized in arrival order to keep the FIFO across the async file I/O. The kap-server edge materializes through the same store with a shared-cache fallback, and the request-time resolver refreshes stale persisted and memoized path tags; a claimed video reference degrades to its tag alone instead of duplicating it. * fix(agent-core-v2): take prompt media intake off the enqueue critical path The record now joins the FIFO synchronously and its daemon-ref intake runs as a per-record promise, awaited by the launch and steer paths before the message is consumed — queue order, list/abort visibility, and prompt submission latency no longer wait on file I/O, and a slow intake no longer head-of-line blocks later prompts. The launching record is tracked so abort and clear stay reachable inside the launch window; startNext re-checks cancellation after every await (intake race, hook, turn admission), a cancelled record is never re-queued, and a compaction requeue waits for onDidFinishCompaction instead of busy-looping the scheduler. * fix(agent-core-v2): record the claiming ref in the media path-tag pairing pairMediaPathTagRefs now exposes claimingRefByTagIndex, and claimingRefIndex reads it instead of recovering the claimer by path equality — which mis-attributed a tag when two different fileIds carried the same path in an interleaved sequence, breaking the pair and leaking the tag as user text. Also covers the memoized-video-tag claimed-drop branch. * fix(transcript): fold upload pairs in user-slash turns and pin pairing parity The cold rebuild's user-slash branch now folds the turn-opening input like any user turn (claimed tag out of the prompt text, one attachment entity), matching the live projection. The ref extraction is consolidated into the contract module (daemonFileRefFromPairingPart, the mirror of the engine's daemonFileRefFromPart) and the mirror carries the new claimingRefByTagIndex map. A new kap-server parity test imports both implementations and asserts identical pairings over shared fixtures, so the engine/mirror pair can no longer drift silently. * fix(kap-server): fold upload media tags out of the search index The global search indexer concatenated every text part of a persisted user message, so the upload pair's <image path> tag made pure-image prompts searchable and wrote the materialization path into the index — breaking the module's documented pure-image invariant and diverging from the live route. textOfContent now folds the pair like every other read model (with a fold-safe coercion for malformed wire parts). Also pins the prompt-media cache-dir fallback with a read-only session media dir test (skipped as root). * feat(node-sdk): re-export the media fold helpers and cover the v1 uploadFile rejection foldMediaPathTagRefs and matchSingleMediaPathTag join the daemon file-reference helper re-exports so hosts can fold the upload tag+ref pair without importing agent-core-v2; the v1 harness's uploadFile not_implemented rejection is pinned by a test. * fix(kimi-code): fold upload pairs in replay/export and keep media tags atomic in steer input Resumed-session replay rendered the upload pair raw — the <image path> tag as user text and the kimi-file:// url as an XML-ish reference — and the markdown export leaked the tag into both the turn body and the overview topic. contentPartsToText and the exporter now fold the pair, and daemon references render as a bare [image]/[video] placeholder. combineSteerInput moves to tui/utils/steer-input and no longer merges a standalone media tag into adjacent text, which would have broken the engine-side pairing for steered image messages. * fix(kimi-code): drop the steer separator before a leading media tag A queued pure-image message opens with a standalone `<media path>` tag, which combineSteerInput keeps atomic. With the previous item ending in a media part, the '\n\n' separator landed as a stranded whitespace-only text part between the media part and the tag, normalizePromptInput rejected the steer, and the already-cleared queue lost the messages. Treat a leading standalone tag as media so the separator is dropped there. * fix: clean staged media lifecycle * refactor(agent-core-v2): narrow the mediaRef root exports and drop a deprecated alias * fix: keep staged media alive through turn * fix(agent-core-v2): reject non-upload ids at the session media store A daemon reference's fileId becomes a storage key in the session media store, but only the file domain validated the id shape — a crafted kimi-file://<id> reaching the request-time resolver's canonical-read fallback could traverse out of the session media dir. Share the file domain's id regex and guard every store entry point: reads miss, materialize declines, and the display path falls back to the hint. * fix(kap-server): project steered prompt content without leaking daemon refs prompt.steered published the raw engine content parts — kimi-file:// refs carrying the absolute materialization path plus the paired <media path> tag — to both the legacy session_event wire (whose schema declares the protocol content shape) and the transcript prompt entity. Route both through one shared prompt-content projection: the upload pair folds into a single {kind:'file'} part, matching the REST prompt list and the no-path-leak rule every sibling surface already follows. * refactor: align daemon-ref naming and drop a duplicate re-export The deprecated videoResolverService alias also re-exported mediaResolvedKey, which made the package root's star exports ambiguous and silently dropped the name. The new transcript contract mirror now uses the canonical daemon-ref vocabulary instead of the deprecated kimi-file spelling. * test(agent-core-v2): pin image abort rethrow, video canonical read-through, release-once Mirror the video abort contract on the new image path (an aborted read cancels the request instead of degrading to a tag), cover the video fallback that uploads the session-canonical bytes after the transient upload is released, and assert the staged-upload release fires exactly once on the intake success path. * fix(kimi-code): bind goal-steer staging leases to the running turn sendMessageInternal read the turn context only after beginSessionRequest had cleared it, so a steer buffered into a running goal turn never got its staging lease bound — the staged daemon upload and cache copies lived until session close instead of being released at the consuming turn's end. Capture the live turn id before the reset (only while a turn is actually streaming; the id outlives its turn otherwise). Also move the staging-lease state machine off the KimiTUI coordinator into a self-contained StagingLeaseTracker with injected effects, drop the duplicate media-tag builder in image-placeholder in favor of the SDK helper, and fix the paste-in-flight comment to match the gate's real granularity. * fix(kap-server): project prompt.queued content without leaking daemon refs The broadcaster projected prompt.steered and stripped turn.started attachments but forwarded prompt.queued raw, leaking kimi-file:// URLs and absolute materialization paths to every subscribed WS connection and the journal. Fold the tag+ref pair into a {kind:'file'} part, same as steered. * fix: keep compressed uploads retrievable and close the steer abort window Two review fixes around prompt media intake: - The compressed re-save was released right after intake (and carried a 1h expiry) while every client read model projects its file id, leaving historical compressed images unfetchable. Keep the re-save as an ordinary upload; roll it back only when preparation or submission fails before the engine takes the prompt. The engine's PromptInput.release hook loses its only producer and is removed. - A prompt aborted while its steer awaited the loop's step assignment was flipped back to 'steered' and its content could still materialize into a later turn. Re-check the reservations after the assignment await and abort the undispatched request when the check fails. * perf(agent-core-v2): memoize inlined image parts across request steps A successful image inline depends only on the immutable upload bytes, so it is memoized per file id (size-bounded) in media.resolved and reused across steps, retries, and media-recovery reprojections instead of re-reading and re-encoding on every request. Degrade forms are never memoized since they depend on the message's tag pairing. Also make the never-empty message placeholder kind-aware (video vs image). * refactor: author media tag+ref pairs in the engine prompt intake Edges (TUI, kap-server REST) now submit bare kimi-file references and the engine intake materializes the bytes, synthesizes the paired media path tag, and falls back to the shared cache dir when the session store is unavailable, replacing per-edge pair construction and duplicate materialization copies. Thread the prompt id from submission through to turn.started (REST prompt_id, WS event, SDK prompt option) so the TUI binds staged-media leases to turns exactly; the origin heuristic stays as fallback and ambiguous claims now surface a staging_lease_invariant telemetry warning. Also lands the pending resendable-extraction fix for cache-hint resubmits after a session switch. * fix: decouple media persistence from prompt intake * refactor(agent-core-v2): project the turn prompt in a single fold pass * test: slim redundant media-ref coverage across layers Fold duplicate pinning of the same media tag+ref rules into shared helpers and it.each tables, and drop assertions that restate behavior already covered at another layer: - drop the kimiFileUrl alias describe (mediaRef.test.ts covers the aliased functions with more cases) - drop pairMediaPathTagRefs describe in favor of the parity fixtures - merge the identical prompt.steered/prompt.queued broadcast tests - parameterize the resolver degradation matrix and prompt intake fixtures (enqueueMedia/gatedImage/expectMediaPair helpers) - drop REST-level context-memory pairing assertions (engine-level intake tests pin the same shapes); keep the caption->system-reminder assertion, the only cover of extractCompressionCaptions - drop the turn-finish-during-intake steer-cancel vector and the switch-session release driver test (unit-level lease tests remain) Net -762 lines; 645 tests green across agent-core-v2, kap-server, transcript, node-sdk, klient, and the TUI. * chore: fix oxlint warnings introduced by image-file-ref changes * fix: harden image file reference lifecycle * fix: close image reference lifecycle gaps * fix: preserve session media paths on replay * chore: streamline image-file-ref changesets * refactor: make daemon media references self-contained, dropping tag+ref pairing A daemon-ref media part now carries everything a read model needs — the kind from the part type and the materialization path from the reference's `?path=` — so prompt intake no longer authors a paired `<media path>` tag, and the pairing/fold machinery (pairMediaPathTagRefs / foldMediaPathTagRefs and their mirror copy) is deleted across the engine, transcript, kap-server, node-sdk, and the TUI. The request-time resolver synthesizes the degrade tag from the reference path whenever bytes cannot reach the provider. Standalone tags stay user-visible text, and never reach the search index or prompt metadata. * fix: reconcile image file references with main after rebase Main removed the agent RPC aggregation layer (agent/rpc) and moved LifecycleScope to app/scopes. Fold the branch's RPC-side behavior into the new structure: PromptPayload carries promptId/disabledTools, and AgentPromptService.submit admits the client-chosen id through the reservation (duplicate rejects before any session state changes) and applies the denylist through toolPolicy. Regenerate the wire/state manifests. * fix(kimi-code): run paste ingestion in the background, wait bounded at submit The paste callback awaited compression + original persistence + the daemon upload while CustomEditor queued every keystroke, so a slow ingestion stalled all typing. Settle the callback once the placeholder lands and track the rest as ImageAttachment.pending; the send path gives a referenced pending ingestion a bounded wait (2s) so paste-then-Enter still submits the compressed/daemon-ref form, and falls back to the inline form when ingestion has not finished. Media-free submits stay fully synchronous. * fix(protocol): mirror prompt_id in the shared prompt submission schema kap-server's local REST schema accepts a client-chosen prompt_id, but the shared promptSubmissionSchema stripped it as an unknown key, so clients validating through @moonshot-ai/protocol lost the id and the turn.started promptId correlation never matched. * fix(klient): normalize file-store errors to public RPC errors on both transports The fileService save/get wire adaptation ran outside the dispatcher's error normalization, so a stale or expired upload id surfaced as the engine's raw Error2 on the memory transport and as a generic 50001 on ipc. Map file.not_found to the public NOT_FOUND RPCError in the shared dispatcher so both transports reject identically, and pin the parity in the conformance suite. * fix(agent-core-v2): keep launching media prompts visible in the queue snapshot startNext shifts the launching record out of pending before its media intake settles, so list()/GET /prompts reported neither an active nor a queued prompt during the intake window even though the submission was accepted and abortable. Report the launching record as still queued, matching the prompt.queued event already published for it. * fix(node-sdk): strip internal promptAttachments from SDK turn.started events The in-process v2 event mapper forwarded the whole domain event, so SDK session.onEvent consumers saw the transcript-projection-only promptAttachments field that kap-server explicitly strips from the WS wire event. Drop it in the mapper so both consumers share the same turn.started field set. * fix(kimi-code): align staging lease id multiplicity with retain count A lease's flat id list conflated two cases: one submission referencing the same image twice (one retain) and a batched steer merging two queued messages sharing the image (two retains). Occurrence-wise release over-consumed in the first case and batch-wise release would under-consume in the second. Dedupe each extraction's ids at the lease creation sites so list multiplicity always equals the retain count, and release one retain per occurrence. * fix(agent-core-v2): check video_in before honoring memoized video uploads The video memo hit path returned a cached ms:// part before the current model's capability check, so switching to a same-provider model with video_in:false sent a video part the model cannot accept instead of degrading to the path tag. Gate on capability first, mirroring the image strategy. * fix(kimi-code): keep recalled queued media staged instead of releasing it Recalling a queued media prompt into the editor is not a discard, but the recall path released the staged files: image attachments lost their daemon upload (resubmit silently downgraded to inline), and a recalled video's cache copy was deleted even though re-materialization needs a source that may already be gone. Recall now consumes only the retain (the next submit re-retains), retires the cache copy to session lifetime, and rebases the video attachment onto that copy. * fix(agent-core-v2): count launching media prompts in prompt.queued queueLength startNext shifts the record into launchingItem before publishQueued computes the count, so a media prompt's prompt.queued reported queueLength 0 even though the prompt is accepted, abortable, and listed as queued. Compute the count from the same snapshot list() exposes. * refactor(agent-core-v2): drop the session media shared-cache fallback Intake keeps the upload-backed reference when the canonical write fails instead of double-writing into an unowned global cache scope; the session media store's reads collapse to the canonical scope, and non-filesystem deployments no longer write every media blob twice. * refactor(agent-core-v2): stop persisting materialization paths in daemon file references The kimi-file:// reference persisted in context memory bundled a durable identity (fileId) with a perishable machine-local absolute path (?path=), which forked sessions and home relocations would stale. The reference now carries only the file id; the display path is derived from the session media store by file id at read time. Parsers tolerate and strip the legacy ?path= query so old records keep resolving. * fix(agent-core-v2): skip atomic-write temp siblings in session media by-id resolution The fs backend stages atomic writes at <key>.tmp.<pid>.<hex> next to the target key, and the media store's prefix-listing predicate matched them, so a lookup racing an unfinished materialize could return the partial copy as the canonical file. * fix(kimi-code): close the staging-lease gap between extraction and dispatch Create the staging lease right after extraction so every pre-dispatch exit releases through the tracker: validation/session failures release it, queueing defers it to the queue item's raw ids/paths, and the cache-hint stash takes over ownership. A forgotten exit now degrades to an unclaimed lease swept at session close instead of a permanently retained upload. The cache-hint restore exits (dismiss, chained restore, session switch during fetch, failed compact/new-session) previously returned only the text to the editor, leaking the extraction's retains and staged cache copies. They now go through queue-recall semantics: retains are consumed, staged copies retire, and recalled videos rebase onto them. * fix(agent-core-v2): bound the inline image memo with a private byte-budgeted LRU A memoized inline image part pins a multi-MB base64 string, and the agent state registry's snapshot/inspect path serializes every registered state in full — so the memo no longer lives in agentState. It is now a private per-file-id LRU with the existing 8MB per-entry cap plus a 64MB total budget; eviction simply re-reads the bytes on the next request. The video memo stays in agentState. * fix(kap-server): fall back to the staged upload on the session media route Prompt intake materializes bytes into the session media store asynchronously and best-effort, but a session_media ref is projected to clients as soon as the prompt is queued — so the download route could 404 during the intake window, and forever after an intake failure. The route now reads the canonical session store first and falls back to the App-scope staged upload, adapting it to the same served shape; only a double miss is a 404. The header note also records that resolving the store resumes cold sessions, an accepted short-term semantic with a TODO for a cold-read channel.	2026-08-17 13:11:28 +08:00
Haozhe	04d23e2dab	fix(agent-core-v2): unify text/binary classification for UTF-8 multibyte files (#2972)	2026-08-17 11:05:33 +08:00
Luyu Cheng	61591bce09	feat(agent-core-v2): bundle multiple skill activations into one prompt submission (#2934) ... * feat(agent-core-v2): support grouped multi-skill prompt submissions Add IAgentSkillService.promptWithSkills: one or more skill activations are validated up front (an unknown or empty submission rejects with no side effects), recorded with a shared submissionId, and enqueued ahead of the prompt through the prompt queue's messagesBefore support, so the whole group materializes atomically as a single turn. Undo cuts, the transcript projection, and the undo precheck treat the group as one unit (stopping at the next anchor even when submission ids collide); hook-result messages are skipped like injections during those walks. Submit hooks run against every message of the group, and user-slash skill activations count as user-submitted content for the UserPromptSubmit hook's origin filter. Surface it through the contract layers: protocol gains submissionId on the user / skill_activation origins and on the skill.activated event (kap-server zod mirrored), klient exposes agentSkillContract.promptWithSkills with parity assertions, and the SDK grows session.promptWithSkills — implemented on the v2 engine and rejecting loudly on the deprecated v1 engine, which is otherwise untouched. * fix(agent-core-v2): reject empty skill lists in grouped prompt submissions - Validate that promptWithSkills receives at least one skill, enforced in the engine and as a non-empty constraint in the klient wire schema. - Restore the released versions and changelog sections for agent-core-v2, klient, and node-sdk that the branch cut had reverted. - Move statement-level narration into the owning file headers per the package comment conventions. - Align the hook-result undo tests with the reachable record ordering (hook results are recorded before the group materializes). * refactor(agent-core-v2): bundle grouped skill activations into the prompt message Replace the submissionId-correlated message group with a single bundled user message: the rendered skill blocks precede the caller's parts in the content, and every activation's metadata rides the prompt origin's new skillActivations field. The bundle is one anchor by construction, so undo needs no group-cutting logic and the messagesBefore prompt seam disappears; the submit hook fires once per submission. skill.activated still fires per skill (transient ops, live-only); resume rebuilds the per-skill view from the prompt origin. Contract chain (protocol, kap-server, klient, node-sdk) drops submissionId accordingly. * fix(agent-core-v2): keep bundled skill blocks out of prompt-facing projections - The transcript cold rebuild expands a bundled prompt's origin skillActivations back into per-skill markers (the live path already projects them from skill.activated events). - turn.started.prompt, the session title excerpt source, and the fork lastPrompt now derive from the caller's own parts, excluding the rendered skill blocks the engine prepends to the bundled content. - Drop the redundant undefined unions from the new origin fields. - Move the activateSkill test narration into the file header.	2026-08-17 00:09:18 +08:00
Haozhe	84da6629b1	refactor(agent-core-v2): decouple workspace from session DI via runtime binding (#2961) ... * refactor(agent-core-v2): decouple workspace from session DI via runtime binding * fix(agent-core-v2): unblock session external hooks and scope workspaceMcp seeds - externalHooksService: inject App-level ISessionManager instead of the unregistered ISessionLifecycleService so SessionStart/SessionEnd hooks actually activate in production; keep sessionId matching and tolerate absent lifecycle events - workspaceMcpService: ignore onWillCreateSession events whose session belongs to another workspace, preventing cross-workspace ISessionMcpHandle seed overrides - update externalHooks integration tests, agent harness, and workspaceMcp tests; add reloadSources coverage in skillCatalog tests * fix(agent-core-v2): honor the bound runtime in prompt context, swarm spawn, and ACP sessions - map system-prompt cwd, directory listing, and additional dirs through RuntimeWorkspaceView, and skip the listing when the bound runtime has no fs capability - pass the caller agent's runtime binding to AgentSwarm child creation and prompt-prefix execution instead of hardcoding local - expose the ACP client filesystem through the ACP session runtime and build its shell/path environment from the probed host instead of hardcoded Linux - dispatch klient facade createChild to sessionManager.createChild so child sessions keep their parent markers * fix(agent-core-v2): resolve routed fs and tool paths with runtime path semantics - WorkspaceFsService resolves via the bound runtime's RuntimePath (extended with basename/dirname) instead of node:path, so mapped roots such as C:\\repo stay runtime-local. - Read/Write/Glob/Grep pass skill roots through mapRoots via RuntimeWorkspaceView input, matching Edit. - acp-server unbinds session runtimes on session/close, not only on delete. - apps/kimi-code drops the /runtime slash command; SDK runtime methods stay. * fix(agent-core-v2): retire idle session controllers, untrack disposed runtime resources, and rebuild fs watches on generation replace * fix(agent-core-v2): resolve oxlint errors in runtime lifecycle fixes * fix(kap-server): untrack download stream from runtime generation on completion * fix(kap-server): drop meaningless void operator on tracked dispose	2026-08-16 20:24:12 +08:00
tpoisonooo	f492cd7c9e	feat(agent-core): add tower command to orchestrate multi-agents (#2633) ... * feat(packages): implement cowork feat(packages): update throttle control feat(agent-core): rename to /tower feat(agent-core-v2): support tower mode fix(packages): keep tower teardown from stranding submodule worktrees A plain `git worktree remove` refuses worktrees containing initialized submodules even when they are clean, so tower teardown silently left behind exactly the worktrees whose workers had run builds (the failure only reached the tool report, never the activity log). The dirty check is the data-loss gate; once it passes, removal always passes --force (harmless on a clean worktree, and precisely what bypasses git's submodule refusal). Kept and failed removals now also land in the activity log as worktree.keep / worktree.remove.failed. feat(packages): allow the tower to AskUserQuestion, workers still cannot The tower-mode AskUserQuestion deny only ever fired on the tower itself: workers never enter tower mode, and their tower-worker profile simply does not list the tool. Drop the deny so the tower can clarify requirements with the human up front; workers and reviewers stay ask-less and escalate via TowerSend. Auto permission mode still disables AskUserQuestion for everyone. fix(agent-core-v2): import LifecycleScope from #/app/scopes main moved the enum out of #/_base/di/scope; follow the new location in the two tower services. test(agent-core-v2): refresh fullCompaction token expectations main's #2699 counts compaction tokens on the full-request basis, so the tower tool schemas (default registry) and the /tower skill catalog entry (system prompt) shift the pinned numbers: +2789 with the default tool set, +173 with the explicit harness tool list. The 20k-window test keeps its shape with a 22k window so the post-compaction floor still fits. feat(agent-core-v2): tower command support secondary model fix(tower): disable todo-list tool feat(tower): reviewer keep primary model fix(tower): tower worker call for authroization update * refactor(tower): drop agent-core-v1 version * feat(tower): remove builtin.ts * fix(agent-core-v2): verify the recorded base branch before tower merges * fix(agent-core-v2): activate tower missions only after a successful spawn * chore(kap-server): correct the search-service activation comment * fix(tower): allowActivationWhileBusy for all skill * update * update --------- Co-authored-by: konghuanjun <konghuanjun@moonshot.ai>	2026-08-16 15:13:42 +08:00
github-actions[bot]	13d86f8b7b	ci: release packages (#2881) ... Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2026-08-14 20:51:17 +08:00
qer	741708f948	feat(kap-server): add plugin marketplace and capability REST routes (#2868) ... * feat(agent-core-v2): surface a machine-key note from capability installs CapabilityEntry.install now resolves an optional note exposed through CapabilityInstallProgress.note (wire-visible). The webbridge entry returns 'user-skill-migrated' when it migrates a pre-existing standalone skill copy onto the plugin-managed one — clients can localize the migration instead of the skill silently disappearing from the user's directory. * feat(kap-server): add plugin management and capability REST routes Expose the App-scope plugin and capability services over the wire so non-CLI hosts (desktop, web) can manage plugins and built-in capabilities end to end: - GET /api/v1/plugins, POST /api/v1/plugins {source}, POST /api/v1/plugins/{id}:{enable,disable,remove} - GET /api/v1/plugins/marketplace — catalog (pluginMarketplaceUrl server option / KIMI_CODE_PLUGIN_MARKETPLACE_URL env / production default) merged on demand with live install state; updateAvailable only on strict semver catalog > installed (no semver dependency) - GET /api/v1/capabilities, GET /api/v1/capabilities/{id}, POST /api/v1/capabilities/{id}:install with client-polled progress - New wire codes 40418 capability.not_found, 40419 plugin.not_found, 40923 capability.install_in_progress, 40924 capability.unsupported Mutations flow through IPluginService, so they serialize with other install paths and fire onDidReload (session skill catalogs and the capability shelf-install hook converge). * fix(kap-server): map plugin input errors to 4xx and correct the unsupported test code - mapPluginError now translates the domain's validation.failed (40001) and fs.path_not_found (40409) instead of collapsing client-fixable input mistakes (relative source, nonexistent local path) into a 50001 internal error - the non-macOS capability install test expected 40923, which this branch assigns to capability.install_in_progress; the unsupported code is 40924 (macOS runners skip the case, which is why it only fails on Linux/Windows CI) * fix(kap-server): resolve catalog-relative marketplace sources and widen the unsupported-test skip - The production CDN catalog carries sources relative to the catalog URL (./official/*.zip); clients handing them back to POST /plugins would hit the local-path normalizer's 40001. Resolve entry sources against the configured catalog URL so every returned source is directly installable. - The 40924 install-rejection test only skipped macOS, but kimi-cu is also supported on Windows x64 — running it there would start the real installer. Skip on every supported platform. * fix(kap-server): accept the legacy url/downloadUrl marketplace source aliases Custom catalogs that the CLI already accepts can carry an entry's source under url or downloadUrl instead of source; the route's strict schema rejected the whole catalog with 50001. Normalize the aliases before validation (same precedence as the CLI parser) so those catalogs keep working through /api/v1/plugins/marketplace. * fix(kap-server): support local marketplace catalogs and drop conditional spreads - KIMI_CODE_PLUGIN_MARKETPLACE_URL accepts a plain path or file:// catalog in the CLI loader; the route only fetched over HTTP, so local catalogs 50001'd for desktop/web hosts. Read local catalogs from disk and resolve their relative sources against the catalog's directory. - Replace the marketplace mapping's conditional spreads with direct possibly-undefined properties per the repo rule. * fix: surface capability install notes through klient and convert file:// entry sources - The klient capabilities contract omitted install.note, so zod parsing stripped it and facade callers (node-sdk, TUI) never saw 'user-skill-migrated'. Add the field and pin it in the facade test fixture. - A marketplace entry source given as a file:// URL fell through to the relative-branch and came back as a garbage path; convert with fileURLToPath so the advertised source stays installable. * test(kap-server): keep the new route tests portable to Windows x64 - The capabilities list assertion treated every non-macOS host as unsupported, but kimi-cu is supported on Windows x64 — derive the expectation from the same platform predicate. - file:///abs/... is not a valid absolute file URL on Windows (no drive root); build the fixture with pathToFileURL from a temp path instead. * refactor: align the capability note and test helper with repo conventions - agent-core-v2 keeps explanatory docs in the top-of-file block only; the note contract already lives in the capability types header, so drop the two member-level doc blocks. - The plugins route test helper sets the optional fetch body directly instead of via a conditional spread. * fix(kap-server): expand ~ in local marketplace catalog paths The CLI loader expands ~/ against the home directory; the route read the path literally, so KIMI_CODE_PLUGIN_MARKETPLACE_URL=~/catalog.json 50001'd for desktop/web hosts while working in the CLI. Share one localCatalogPath helper (file:// conversion + tilde expansion) between the catalog read and the relative-source resolver. * fix(kap-server): expand home-relative marketplace entry sources A catalog entry with source '~/...' fell through to the catalog-relative branch and came back as <catalog-dir>/~/... — unresolvable by POST /plugins. Expand ~ via the shared helper before the absolute/relative decision. * fix(kap-server): match CLI field semantics for source aliases and stub the Windows home - A blank or non-string source no longer shadows the url/downloadUrl aliases; the first valid (non-blank, trimmed) of source/url/downloadUrl wins, mirroring the CLI parser's stringField. - The tilde test also stubs USERPROFILE so os.homedir() resolves to the fixture home on Windows runners. * fix(kap-server): read a blank marketplace tier as missing The CLI parser trims tier and treats a blank as absent (third-party); the route's enum rejected the whole catalog with 50001. Normalize the tier alongside the source aliases in the same preprocess. * fix(kap-server): derive marketplace versions from GitHub release sources Entries that omit version but encode it in a GitHub release/tag (or tree/commit) source never surfaced updateAvailable. Derive the version from the resolved source — same URL shapes as the CLI parser, validated with the route's strict x.y.z rule (no semver dependency). * fix(kap-server): fail catalog validation on a source with no usable value A whitespace-only source with no valid alias passed z.string().min(1) untrimmed and resolved against the catalog URL into nonsense. Drop the key during normalization so the schema reports the entry as missing its source (same outcome as the CLI's 'must define source'). * fix(kap-server): resolve latest versions for bare GitHub marketplace entries A catalog row whose source is a bare GitHub repo (the production curated rows are shaped this way) kept version undefined, so updateAvailable never fired for exactly the entries most likely to update. Resolve the latest release tag through the /releases/latest redirect — the UI route, not the rate-limited API — same as the CLI, degrading to no version on any failure. * docs(kap-server): note the marketplace version resolution in the plugins route header * feat(kap-server): mark capability wiring rows in the marketplace response A client following only /plugins/marketplace + POST /plugins would install a capability's wiring plugin without its binary runtime, with no wire-level way to tell. Entries whose id matches a capability's wiring plugin now carry capabilityId, so clients route them through /capabilities/{id}:install — the client-side routing pattern the CLI established (the upstream design that replaced the server-side hook). * fix(kap-server): fall back to the source-checkout catalog for the default location When the marketplace location is the built-in default (no server option or env override) and the fetch fails, read the repo checkout's own plugins/marketplace.json — the CLI loader's behavior for offline source-checkout dev. An explicitly configured catalog still fails hard with 50001. Bundled installs have no checkout file, so the fallback simply never fires there. * fix(kap-server): resolve fallback catalog sources against the fallback file readMarketplaceCatalog returned only the JSON, so entries from the source-checkout fallback resolved their relative sources against the (unreachable) CDN URL — coming back as unusable https paths instead of local directories. The reader now returns the location actually read, and source resolution uses it. * fix(kap-server): honor the CLI's marketplace metadata aliases Custom catalogs using name / shortDescription / websiteURL (accepted by the CLI parser) lost those fields to schema stripping, falling back to the entry id. Normalize the aliases in the same preprocess as the source/tier normalization. * fix(kap-server): filter marketplace keywords instead of rejecting the catalog A keywords array with non-string or blank members failed the strict schema and took the whole catalog down with 50001. Normalize to the CLI parser's semantics: non-array reads as missing, arrays keep trimmed non-blank strings only. * fix(kap-server): treat a blank or non-string marketplace version as missing The CLI parser reads version through its lenient stringField and falls through to source-derived versions; the route's schema rejected a numeric version with 50001 for the whole catalog. Normalize version in the preprocess like the other fields — the gh-plugin fixture now carries a numeric version and still derives 2.0.0 from its tag source. * fix(kap-server): trim marketplace entry ids before the install-state join A whitespace-padded id survived validation raw and never matched the installed records (updateAvailable silently lost). Normalize the id in the preprocess — trimmed, blank rejected — matching the CLI's requiredString. * fix(kap-server): gate capability markers to the default catalog A custom catalog (env or server option) may legitimately carry a same-id fork of a capability's wiring plugin; marking it capabilityId would route users to the built-in install. Apply the marker only for the default catalog (including the source-checkout fallback), matching the CLI injecting built-in rows only for the default catalog. * fix(kap-server): compare marketplace versions with real semver The hand-rolled strict x.y.z check rejected valid semver the CLI accepts (v-prefixed, prerelease tags), so updateAvailable diverged between CLI and wire clients. Take the semver package (already in the monorepo via the CLI) for the update check and the two source-derived version validators. * fix(kap-server): validate marketplace entry types and count the dev server as default - Custom catalog rows with an unsupported type (e.g. integration) were stripped by the schema and advertised as installable plugins; the CLI rejects the catalog outright. Model the same plugin/managed/guide vocabulary. - scripts/dev.mjs marks its repo-owned catalog with KIMI_CODE_PLUGIN_MARKETPLACE_FROM_DEV_SERVER=1 — honor the flag in the isDefault check so capability markers and the checkout fallback behave exactly like the CLI under the dev marketplace. * fix(kap-server): join capability rows through their platform wiring plugin id kimi-cu installs its wiring plugin as kimi-cu-win on Windows x64, so a catalog row keyed kimi-cu never matched the installed record there (no installed state, no updateAvailable). The row mapping now knows each capability's wiring plugin ids and joins through them. * fix(kap-server): map plugin load failures to 40001 An install source pointing at a directory/zip with a missing or invalid manifest throws plugin.load_failed — a client-fixable input error that fell through to 50001. Map it to validation.failed alongside the other input mistakes. * build(kap-server): align @types/semver with the workspace version sherif rejects multiple workspace versions of one dependency; the CLI pins @types/semver at ^7.7.0. * refactor(agent-core-v2): share the plugin marketplace client/parser across hosts The kap-server marketplace route grew its own copy of the CLI's catalog loading/parsing logic (lenient aliases, blank-means-missing fields, source resolution, GitHub version derivation) — two implementations of a public, hand-writable format would drift on every catalog change. Move the read/parse/version machinery into the plugin domain as app/plugin/marketplace (pure functions, no DI): the CLI keeps a thin wrapper owning configured-source resolution and its checkout fallback, and the route keeps only the wire concerns (install-state merge, capabilityId markers, error envelopes). plugins.ts drops ~230 lines of duplicated machinery. One deliberate behavior fix rides along: tilde entry sources now expand against the home directory at parse time (the CLI previously passed them through literally, failing later at install validation). * docs(agent-core-v2): fold the marketplace module's member docs into the file header The package convention keeps explanatory comments in the top-of-file block only; the moved parser carried several function/member-level JSDoc blocks from its CLI home. The header now carries the format contract, leniency rules, source/version resolution order, built-in masking semantics, and the fallback gating rule. * docs(agent-core-v2): drop the remaining statement comments in the marketplace module The header carries the rationale (update semantics, GitHub ref shapes, the releases/latest choice); the convention allows nothing beside statements. * fix(kimi-code): import the shared marketplace module by its deep path constant/app.ts is evaluated on every CLI invocation; re-exporting from the agent-core-v2 root would pull the whole engine module graph into startup. The package's wildcard subpath export lets both CLI files take only the pure marketplace module (node builtins + semver). * feat(kap-server): fan plugin and capability lifecycle out as global WS events Clients currently poll the plugins/capabilities REST surfaces and can hold stale rows while another client mutates the set. Publish two global events instead: - event.plugin.changed — fired off IPluginService.onDidReload, so any install/enable/disable/remove from any client reaches every host - event.capability.changed — every capability install progress transition (CapabilityService gains onDidChangeInstall), so rows update live and settle is observable without polling Both ride the existing global fan-out (no subscription needed) and are documented in the wire schema registry. * fix: register the lifecycle events in the wire union and tidy the contract header - event.plugin.changed / event.capability.changed were declared but not part of agentEventSchema, leaving the wire catalog incomplete. - The onDidChangeInstall member doc moves into the capability contract file header (package comment convention). * feat(protocol): mirror the plugin/capability lifecycle events in the shared WS schema Clients and e2e harnesses validating server frames against @moonshot-ai/protocol would reject event.plugin.changed / event.capability.changed. Register both in the shared catalog (TS interfaces, zod schemas, and both unions), matching the model_catalog.changed precedent for global events. * fix(kap-server): prefer the platform wiring plugin when joining capability rows A stale same-id record (e.g. a raw kimi-cu plugin next to the real kimi-cu-win wiring on Windows x64) previously won the join, showing the wrong installed state and update availability. Capability rows now join through the wiring plugin ids in platform preference order before falling back to the catalog id. * fix(kap-server): put the github metadata of plugin summaries on the wire schema GitHub-sourced plugin summaries carry github {owner, repo, ref, installedSha} from the domain; the route serializes raw domain objects, so the field reached clients undocumented. Declare it in pluginSummarySchema so the OpenAPI surface matches reality. * test(node-sdk): cover the new lifecycle events in the exhaustive switch The event-type exhaustiveness test broke when the shared protocol union gained event.plugin.changed / event.capability.changed. * fix(kap-server): mark capability progress events volatile Per-chunk download progress transitions ride the same fan-out as durable frames and were being persisted to the __global__ journal — hundreds of stale frames per install. event.capability.changed is live-only state, so it joins the volatile list alongside event.di.unit_changed; the settle frame stays recoverable via a direct capability read. event.plugin.changed remains durable (rare, and a reconnecting client should replay it). * feat(kap-server): inject built-in capability rows into the default catalog response The checked-in production catalog carries kimi-webbridge but not kimi-cu — the CLI injects built-in rows client-side, so wire clients never saw Kimi Computer Use in /plugins/marketplace. For the default catalog the route now appends supported capabilities the catalog lacks (static descriptors via ICapabilityService.describeCapabilities — no detector probes), marked with capabilityId and a capability:<id> sentinel source so installs still route through the capability surface. * fix(kap-server): run injected capability rows through the install-state join The injected kimi-cu row hardcoded installed: undefined, so an already-installed capability still read as installable. Injection now happens before projection, so injected rows get the same backing-plugin join (installed state, update badge, capabilityId marker) as catalog rows. Also moves the describeCapabilities note into the contract header (package comment convention). * test(kap-server): gate the injected-row assertions on platform support kimi-cu injects only where supported (macOS / Windows x64); on Linux CI the row is correctly absent. * fix(protocol): classify capability progress as volatile in the shared catalog kap-server never journals event.capability.changed (it is in the server-local volatile list); shared-protocol clients reading isVolatileEventType would treat per-chunk progress frames as durable and replayable. Mirror the classification. * fix(kap-server): hide capability rows on unsupported platforms Catalog-carried capability rows (kimi-webbridge in the default catalog) were marked with capabilityId regardless of host support — on an unsupported platform clients would route into an impossible capability install. Rows whose capability is unsupported are now excluded from the default-catalog response entirely (the CLI hides its built-in rows the same way).	2026-08-14 15:45:34 +08:00
7Sageer	249d8faa34	fix(agent-core-v2): mint interaction ids engine-side (#2911) ... * fix(agent-core-v2): mint interaction ids engine-side Self-hosted OpenAI-compatible endpoints may renumber tool call ids on every response (Bash_0, Bash_1, ...). The approval/question/user_tool facades used the provider toolCallId as the interaction id, so a repeated id was silently swallowed by client-side pending-interaction dedupe: the approval prompt never appeared and the turn parked forever (#2908). Interaction ids are now minted by the engine (approval_<uuid> / question_<uuid> / user_tool_<uuid>); the provider toolCallId stays on the payload for correlation. This matches v1 semantics, where the approval id was already a daemon-minted id independent of the tool call id. * fix(agent-core-v2): normalize duplicate provider tool call ids at ingestion Self-hosted OpenAI-compatible endpoints may renumber tool call ids on every response (Bash_0, Bash_1, ...), and every downstream keying assumes an id identifies exactly one call: context rebuild silently drops the second tool result with a duplicated id, the strict projector discards duplicate calls, transcript frames merge, and approval/activity correlation misfires. A per-agent ToolCallIdNormalizer in the llmRequester stream boundary now tracks ids already claimed (seeded from the restored context). The first occurrence passes through unchanged; later occurrences — across responses or within one — are rewritten to a readable <id>__<n> suffix, kept consistent between streamed deltas and the finalized message, and logged for provenance. A failed attempt rolls its claims back so a projection retry re-streams the same logical calls under the same ids. * fix(agent-core-v2): thread the minted approval id through events and status The permission.approval.requested/resolved events only carried the provider toolCallId, so AgentActivityView exposed approvalId = toolCallId and the agent.status.updated approval phase forwarded an id that POST /sessions/{sid}/approvals/{id} cannot resolve — the kernel parks under the minted approval_<uuid>. Mint the interaction id at the agent call site and include it in the approval request payload: the kernel honors the explicit id, the events carry it, and the activity view keys pendingApprovals by it (falling back to the toolCallId for id-less events). * fix(agent-core-v2): surface minted interaction ids in facade listPending The approval/question facades returned only the original payload from listPending(), so once the kernel id stopped deriving from the provider toolCallId, hosts listing pending requests had no id to feed back into decide()/answer()/dismiss() without reaching into the kernel. Merge the parked interaction id into each returned request — the klient contract schemas already carry the optional id field, so the RPC surface becomes round-trippable as well.	2026-08-14 14:47:00 +08:00
weiwei Wang	53909d91e3	fix(kimi-web): cache content-hashed assets (#2865)	2026-08-14 13:08:30 +08:00
Haozhe	cb30a7799d	fix(kap-server): expose parent_tool_call_id and subagent_type in /tasks responses (#2912)	2026-08-14 13:03:56 +08:00
Haozhe	eb72aebeeb	fix(kap-server): remove the 64 MiB web session export limit (#2910)	2026-08-14 11:48:56 +08:00
Haozhe	325913a532	feat(kap-server): expose the subagent registry id in /tasks responses (#2907)	2026-08-14 11:28:07 +08:00
7Sageer	5857ba23b0	test(kap-server): deflake three timing-sensitive tests (#2894) ... * test(kap-server): poll the read-model immediate-read assertions The 'prepares the read model at boot and serves immediate reads' test sampled the session list / workspace session_count / paged read exactly once after creating a session. While a mirror flush is in flight its batch is only per-shard atomic and the pending-queue cleanup is not linearized with reads, so a single-sample read landing inside that window can transiently miss or double-count the new session (seen twice on main CI as 'expected false to be true' and 'expected 0 to be 1'). Poll with vi.waitFor instead; the transient lasts at most one in-flight flush (~100ms cadence). * test(kap-server): retry the transcript test temp-dir teardown rm The engine's file log writers flush synchronously on scope dispose but their trailing async close can still create a file under the test home after server.close() resolves, so the afterEach rm occasionally fails with ENOTEMPTY on a loaded CI runner. Retry the rm (maxRetries: 5), matching the existing pattern in questions.test.ts / fs.test.ts. * test(kap-server): drain the in-flight search sync before appending The 'serves the published generation without waiting for a blocked background sync' test appended the delta right after a warm-up search that had kicked a fire-and-forget background sync pass. On a starved CI worker thread that pass can read the file after the append and publish both documents early ('expected 2 to be 1'). settleSync before the append makes 'no pass can index the delta' structural.	2026-08-13 21:02:34 +08:00
Haozhe	4425409cea	fix(features): retract contributed service metadata (#2886) ... * fix(features): retract contributed service metadata - tie contributed service discovery to feature disposal - reject duplicate providers for the same scope and service - cover feature unload and debug channel resolution * test(features): preserve contributed service registry - remove the global contributed-service test reset - keep provider cleanup local to each regression test * fix(features): scope service discovery to each app - store feature service metadata in the app-local collection tree - bind debug lookup and test overrides to the owning app root - keep duplicate provider activation atomic within one app	2026-08-13 19:13:00 +08:00
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
Haozhe	314b39489e	refactor(agent-core-v2): extract swarm into a scope-organized feature (#2874) ... * refactor(agent-core-v2): extract swarm into a scope-organized feature - move src/agent/swarm, src/session/swarm, and src/agent/tools/agent-swarm into src/features/swarm/{agent,session,tools/agent-swarm}; swarmOps.ts stays a static import=register wire channel at the feature root - add SwarmFeature carrying the three runtime registrations (IAgentSwarmService, ISessionSwarmService, IAgentSwarmTool) with ScopeActivation.OnScopeCreated preserved - switch src/index.ts to precise leaf exports and update import sites, including the kap-server and kimi-inspect deep-path imports - move tests to test/features/swarm and re-assert service overrides in the test harness so stubs keep winning over feature contributions * fix(agent-core-v2): keep feature-contributed tools in Agent tool descriptions SubagentTool.knownToolReferences() now reads the full AgentToolContribution collection (static registrations and feature contributions alike) instead of the static contribution table. A caller profile that does not activate a feature-contributed tool (e.g. AgentSwarm) no longer drops it from the per-profile tool listings the description advertises for spawned profiles when a workspace/session restriction forces explicit enumeration. Add a regression test with a caller profile lacking AgentSwarm under a global tool restriction. * refactor(kap-server): lift session profile updates to the route edge - add sessionProfile.ts/sessionAgentConfig.ts route helpers that resume the session and dispatch title/metadata and the agent_config patch to the native v2 services directly - drop updateProfile from ISessionLegacyService, leaving only the status rollup and the goal read in the legacy adapter - wire shape and client-visible behavior unchanged	2026-08-13 13:35:49 +08:00
7Sageer	c9bfe8b2c8	feat: replace the secondary-model experiment with a declarative subagent model pool (#2700) ... * feat: replace secondary-model experiment with [subagent.models] pool Add a declarative subagent model pool to agent-core-v2: [subagent.models] maps [models] entry ids to selection hints rendered in the Agent/AgentSwarm tool descriptions, and [subagent].default_model picks the spawn model when the caller passes none. The tools' model parameter becomes a free-form alias string (stripped when no pool is configured), description rendering is caller-aware (primary (alias) [main model]), and a session-start validation service fails fast with CONFIG_INVALID on a missing/invalid default_model or an unresolvable pool alias. Remove the secondary-model experiment from the v2 engine, node-sdk, kap-server, and the TUI (the /secondary_model command), and drop the agent-profile modelPreference / model_preference frontmatter field on v2. The legacy v1 engine keeps the experiment unchanged; v2 ignores leftover [secondary_model] config silently. * fix(agent-core-v2): harden subagent model-pool validation and error/picker mapping Deep-review follow-ups to the [subagent.models] pool: - validate the pool before session materialization (after config.ready) and before the fork file copy, so a broken pool no longer leaves orphaned session dirs or leaked MCP overlay connections; the Session-scope validation service stays as a backstop - reject the reserved "primary" pool alias at startup, and again defensively in resolveSubagentBinding so a pool broken by a runtime config edit fails loudly at spawn instead of binding the wrong model - keep the [default] marker when the caller's own model is the pool default (primary (alias) [main model] [default]) - recompile the cached tool-args validator when a tool advertises a new schema object (mid-session pool edits no longer hit a stale validator) - map config.invalid to VALIDATION_FAILED in kap-server's session routes, the debug transport mapper, and the catch-all error handler - hide the v1-synthesized __secondary__ entry from the /model and /provider pickers again - fold per-export doc blocks into file headers per package comment conventions; add pre-flight/reserved-key/validator/mapping tests and document that create/resume/fork all fail on a broken pool * feat: re-add /secondary_model and accept a lone subagent default_model - v2 engine: a pool-less [subagent] default_model forms an implicit single-entry pool — validated at session create/resume/fork like an explicit pool, and advertised through the Agent/AgentSwarm model parameter. - Tool descriptions: the caller's own alias is a normal pool entry marked [main model]; the primary line stays distinct because only it inherits the caller's thinking level. - TUI: /secondary_model returns, persisting [subagent] default_model (merging into an existing pool with an empty description); the picker hides the no-op Thinking footer and rejects the reserved primary alias. - kap-server: /api/v1/config accepts and echoes subagent; the snake-to-camel patch conversion preserves user-defined map keys under providers/models/experimental/raw without leaking preserve mode into a colliding alias's own fields. - v1 config schema learns subagent.defaultModel/models so the shared config.toml round-trips; the v1 engine still ignores them at runtime. - Docs (en/zh) and changesets updated. * docs: use public model identifiers in the subagent model pool examples * refactor: rename /secondary_model to /secondary-model * test: cover the /secondary-model command name resolution * Revert "test: cover the /secondary-model command name resolution" This reverts commit 98a4a6d999. * feat(agent-core-v2): move the subagent model pool to [secondary_model] The pool keys (default_model, [secondary_model.models]) now live in their own [secondary_model] config section instead of [subagent], which keeps only timeout_ms; legacy [subagent] pool keys are ignored with a deprecation warning. The SDK config contract carries the pool on the secondaryModel field, so the TUI /secondary-model command (now also aliased /subagent-model) and the kap-server /config wire read and write it directly with no translation layer. * docs: correct default engine guidance * feat(agent-core-v2): pin subagents to default_model with [secondary_model] force force = true removes the main agent's per-spawn model choice: the Agent and AgentSwarm tools stop advertising the model parameter and every spawn binds default_model; an explicit choice, "primary" included, is rejected. The setting requires default_model, rejects a [secondary_model.models] table, and is validated loudly at session create/resume/fork (lifecycle preflight plus the Session-scope backstop). The v1 engine declares the key for write round-trips and excludes it from the recipe patch. Also documents pool entries as per-alias thinking-level variants via default_effort overrides. * docs: use real managed model aliases in the secondary_model examples The pool examples invented aliases (kimi-hs, fable, codex) and referenced non-existent model IDs (model = "codex"); they now reference only the managed aliases provisioned by /login (kimi-code/k3, kimi-code/kimi-for-coding, kimi-code/kimi-for-coding-highspeed), with the effort variant derived as kimi-for-coding-highspeed-deep. Also replaces the versioned kimi-k2.5 alias with kimi-for-coding per the docs model-ID rule. * chore: simplify the subagent model pool changeset * feat(agent-core-v2): honor the legacy [secondary_model] model key as a fallback default * refactor(node-sdk): export the reserved model-alias constants from the SDK Restore the SECONDARY_DERIVED_MODEL_ALIAS re-export and add PRIMARY_SUBAGENT_MODEL_CHOICE so the TUI imports both from @moonshot-ai/kimi-code-sdk instead of vendoring local copies. * feat(agent-core-v2): keep the subagent model pool behind the secondary-model experiment Restore the secondary-model flag gating so this change only adds the pool: with the experiment off the [secondary_model] pool keys stay inert — the Agent/AgentSwarm tools strip the model parameter, spawns inherit the caller's model, and startup pool validation is skipped. The /secondary-model slash command is gated behind the experiment again, and the docs and changeset describe the flag. * fix(node-sdk): cascade provider removal into the subagent model pool Deleting a provider left [secondary_model] entries pointing at the removed model aliases; with the secondary-model experiment on, every subsequent session create/resume/fork then failed pool validation. planProviderRemoval now filters dangling pool entries, and drops the whole section when its effective default (defaultModel, or the legacy recipe's model fallback) dangles — folded into the same atomic multi-section replace. * fix(agent-core-v2): close two subagent model pool validation gaps Spawn-time resolveSubagentBinding now rejects force combined with a [secondary_model.models] table, matching the startup pre-flight — a live session could otherwise reach that invalid state through a deep-merged config patch and only fail on the next create/resume. The session lifecycle pre-flight also awaits the kosong model/provider registries' ready alongside config.ready, so a cold bootstrap no longer fails a valid pool with CONFIG_INVALID against an empty registry. * test(agent-core-v2): stub the model/provider registries in handler-chain tests SessionLifecycleService now awaits IModelService/IProviderService readiness in its pool pre-flight, so the tests that assemble the real service through a hand-built container must register the two tokens. * fix(kap-server): cascade REST provider deletion into the subagent model pool The DELETE /providers route rewrote only the providers and models sections, so a pool referencing one of the deleted provider's aliases was left dangling and the engine's create/resume/fork pool validation failed every subsequent session until the user repaired the TOML by hand. Filter dangling pool entries and drop the section when its effective default dangles, mirroring the SDK's planProviderRemoval semantics. * fix: keep the subagent pool consistent on provider replace and preserve legacy recipe fields PUT /providers rebuilds the provider's alias set and can drop or rename aliases referenced by [secondary_model]; the pool now cascades there too — renamed aliases are repointed (mirroring the global default-pointer migration), dropped aliases are filtered, and the section is cleared when its effective default dangles. The v2 [secondary_model] schema also declares the legacy recipe patch fields (default_effort, max_output_size, ...) so validation no longer strips them: pool resolution keeps ignoring them, but config reads/writes now round-trip losslessly instead of silently deleting them from config.toml on any pool write. * fix(agent-core-v2): cascade the subagent pool on catalog refresh writes A background provider/model refresh rewrites the [models] table without touching [secondary_model], so a dropped alias left the pool dangling and every subsequent session create/resume/fork failed validation until the user repaired the TOML by hand — the same gap the SDK and REST write paths already had, but triggered unattended. The cascade helper now lives in agent-core-v2 next to the section it protects (cascadeSubagentModelPool): the discovery service folds the pool into the same atomic replaceSections transition, and kap-server's provider write routes reuse the shared helper instead of a local copy. * fix: cover the last two model-table write paths for the subagent pool ModelsDevImportService's catalog and custom-registry imports rebuild the [models] table without the pool cascade, so an import that drops a pooled alias left a dangling pool behind; both final write passes now fold the pool through cascadeSubagentModelPool (the drop passes deliberately skip it). The StubConfigService test double now treats a null section value as a delete, matching the real ConfigService. The TUI's provider overwrite flow removes an existing provider before re-adding it, which ran the removal cascade against a model table where every alias of that provider was absent and silently dropped the pool; the flow now snapshots secondaryModel up front and restores the entries that survive the re-add, via the cascade helper re-exported from the SDK.	2026-08-13 12:29:03 +08:00
Haozhe	23e68eee8b	refactor(agent-core-v2): remove the agent RPC aggregation layer (#2871) ... * refactor(agent-core-v2): remove the agent RPC aggregation layer - delete src/agent/rpc/ (AgentRPCService, IAgentRPCService, core-api, prompt-metadata, types) and sink each method's orchestration into its owning domain service - prompt: new submit/submitSteer composing disabledTools gating, MAIN-only session metadata, and engine-side {turn_id} settlement - skill: activate now returns PromptLaunchResult and writes session metadata internally (MAIN-only, unified across prompt/steer/skill/ pluginCommand); node-sdk and kap-server drop their edge-side writes - pluginCommand: new agent-scope domain owning command activation and the plugin_command.activated domain event - permissionMode/loop/fullCompaction: new setModeAndBroadcast / cancelFromUser / cancel; setMode and loop.cancel stay pure for internal callers - klient: agentRpcContract split into per-domain contracts; facade re-routes to domain channels with its public API unchanged - node-sdk, kap-server, kimi-inspect and the v2 test harness now call domain services directly; ctx.rpc keeps its name as a composed adapter - externally visible: the agentRPCService debug channel is gone and session metadata writes are now MAIN-agent-only (see changeset) * refactor(agent-core-v2): move disabledTools gating out of the prompt domain Prompt should not own session tool policy: submit no longer accepts or applies disabledTools. The klient facade keeps its prompt({ disabledTools }) API and composes it edge-side — applying agentToolPolicyService setSessionDisabledTools before calling agentPromptService.submit, the same way kap-server's prompt route already does. Over klient, a profile-less engine now surfaces the raw profile error instead of request.invalid. Also restores the RPC-removal changeset, which did not make it into the previous commit. * chore(agent-core-v2): drop the RPC-removal changeset * refactor(klient): drop disabledTools from the prompt entry entirely The prompt path no longer carries session tool gating on any surface: the klient facade prompt() loses the disabledTools field and calls agentPromptService.submit directly, and the node-sdk SessionPromptRpcInput stops accepting or forwarding it (v1 always ignored the field). Session tool gating remains available through IAgentToolPolicyService.setSessionDisabledTools, composed at the edge the way kap-server's prompt route does; the klient toolPolicy contract added for facade-side composition is removed as unused.	2026-08-13 10:57:01 +08:00
liruifengv	43c68f58f5	feat(agent-core-v2): keep session updatedAt stable across meta management writes (#2815) ... * feat(agent-core-v2): keep session updatedAt stable across meta management writes Rename, archive/restore, and fork no longer bump a session's updatedAt, so recency-sorted session lists stop reshuffling on management actions: - setTitle/setArchived pass touchUpdatedAt: false; an explicit patch.updatedAt always wins (fork inherits the source's recency, so a fork lands next to the source instead of floating to the top) - new SessionMeta.archivedAt records the archive moment (cleared on restore) and is surfaced through the session index, the v1/v2 session routes (archived_at), and the klient contract, so the archived list keeps an accurate archive time without relying on the updatedAt bump * fix(agent-core-v2): normalize a legacy ISO-string updatedAt when forking a cold session A cold legacy/v1 state.json read from disk can still carry an ISO-string updatedAt; passing it through as the fork's explicit patch.updatedAt would persist a string into the v2 metadata. Normalize with toEpochMs (falling back to now when absent/unparseable). * fix(agent-core-v2): write fork metadata after agent recreation Registering each copied agent during fork is an ordinary metadata write that bumps updatedAt, which overwrote the inherited source recency and still floated normal forks (sessions with agents) to the top. Move the fork's metadata update after the agent recreation loop so the inherited updatedAt is the final write. * fix(agent-core-v2): preserve persisted recency when restoring a cold session Resume creates the main agent for a cold session that has no persisted agents.main entry (e.g. an empty session), and that registration bumps updatedAt — so unarchiving an empty session still floated it to the top. Capture the index summary's updatedAt before resume and re-apply it in the restore write (archived:false, archivedAt cleared, explicit updatedAt wins over the bump). * fix(agent-core-v2): make agent registration non-touching for recency Registering an agent is a structural write, not content activity — but it went through an ordinary metadata update that bumped updatedAt. That reordered recency-sorted listings whenever materialization created an agent: resume of a cold session without a persisted agents.main (so archive-via-resume and restore of empty sessions still floated), and runtime subagent registration mid-turn. registerAgent now passes touchUpdatedAt: false; restore goes back to the plain unarchive write and no longer needs the capture/reapply workaround. * fix(agent-core-v2): duplicate cron tasks only after the fork metadata is durable With the metadata write moved after agent recreation, cron duplication ran before it — a rejected metadata update left cloned cron records pointing at a fork whose directory the catch block just removed. Keep cron duplication after the durable metadata write. * style(agent-core-v2): fold new invariants into module headers The package convention keeps comments in the top-of-file block only — move the touchUpdatedAt precedence, non-touching registration, and fork ordering notes out of statement-level positions into the respective module headers. * chore: scope the changeset to agent-core-v2	2026-08-12 13:40:26 +08:00
Haozhe	26a37f30a3	fix(kap-server): restrict debug RPC fallback to feature-contributed services (#2808) ... The decorator-registry fallback resolved every decorator name, including kernel tokens like instantiationService — a call to instantiationService/dispose would tear down the root container. Record Feature.contributeService tokens in a contributed-service table and fall back to that table only, so runtime-contributed services stay callable while unregistered kernel tokens remain unreachable.	2026-08-12 12:35:01 +08:00
qer	619564dcf9	fix(kap-server): add WebSocket heartbeat to survive proxy idle timeouts (#2813) ... The v1 WS connection had no keepalive: by design it stayed open until the client disconnected, which only holds for direct connections. Behind a reverse proxy or gateway with an idle timeout (30s defaults are common), any quiet stretch — e.g. waiting on a slow model response — got the connection killed, surfacing as a recurring 'Realtime connection error' in the web UI. Send an application-level ping every 10s and advertise heartbeat_ms in server_hello (the schema and all shipped clients already answer pong). Application-level rather than protocol-level ping because browser JS cannot observe the latter, and the client's stale-socket detector keys on incoming message frames. Any inbound frame refreshes liveness; after two silent cycles the connection is presumed half-open and closed with 1001 so dead peers get reaped instead of leaking.	2026-08-12 00:28:03 +08:00
Haozhe	860354976e	feat(agent-core-v2): add event-subscription introspection (#2806) ... - name Emitters and surface their subscriptions as on:<name> ledger labels through a named EventSubscription class and IDisposableDebugLabel - add IDebugEventsService.subscriptions(), merging unit-book entries with per-bus listener counts, contributed at App scope by the new debugEvents feature - kap-server debug dispatcher falls back to the global decorator registry so runtime-contributed services stay callable - kimi-inspect: add an Events panel to the DI view	2026-08-11 14:55:08 +08:00
Haozhe	7cd64766c8	feat: isolate the full-text search index from the session index and the main thread (#2701) ... * feat(minidb): instrument open lifecycle with phase timings and status Add MiniDb.lifecycleStatus() exposing the no-generation/generation-load/ wal-catch-up/full-rebuild/ready/degraded state machine plus per-phase timings (generation candidate load, store/non-text/text image load, postings integrity check, WAL scan/apply, full recovery, text rebuild hosting), so snapshot load, WAL catch-up and full rebuild can be told apart in diagnostics. Also add a repeatable open-lifecycle bench (small data, large WAL delta, large full-text generation, corrupt generation) and fixtures proving a healthy generation open performs no full-corpus tokenization while a corrupt or missing generation falls back. Log search-index and query-store open diagnostics in kap-server and agent-core-v2 so a listSessions call can be attributed to the database it touches. No persistence format or product behavior change. * feat(agent-core-v2): isolate the session index from the global search index Harden the separation between the session read model and the full-text search index so session operations never depend on search availability: - Reject text index definitions in MiniDbQueryStore at definition level, keeping the session query-store a structural-only read model with no postings/tokenizer artifacts, and assert its generation carries no full-text files. - Share one authoritative scan between the first list and the initial projection (single-flight) instead of scanning twice; reads may only join an in-flight scan, and every fallback read folds the mirror's pending queue so read-your-writes holds while preparing. - Keep withReadModel() fallback semantics pinned by tests: uninitialized/preparing reads hit authoritative metadata immediately, ready reads use the read model, degraded keeps falling back with a diagnosable status reason. - Guard session metadata writes so a mirror failure degrades only the read model and never fails the session lifecycle. - Prove via tests that listSessions/--resume/--continue never open the global search DB (including when search-index is unopenable), and that only real full-text search requests report building/stale/degraded. * perf(minidb): slice open-time work so it never blocks the main thread Make the whole generation-open path cooperative: - Replace the synchronous postings/store CRC verification with chunked async variants (readGenerationFileCheckedAsync, verifyFileIntegrityAsync) that keep the exact bytes/crc-mismatch error semantics. - Give the WAL-delta apply a primitive-op + wall-clock budget (walApplySlicer), so a batch frame unrolling into thousands of ops can no longer run as one uninterruptible slice; torn-tail, corrupt-batch and read-only behaviors are unchanged. - Slice the big attach loops: Store.bulkLoadRefsAsync + SkipList.bulkLoadAsync for the store image, async parsers and loadImageAsync for secondary/compound images, and TextIndex.attachImageAsync for the docs/dictionary map construction. - Queue text builds on worker-slot pressure (WorkerSlots.acquireBounded, bounded by MiniDb.textBuildSlotWaitMs, abort-aware) instead of falling back to an unbounded inline build; a persisted drought hosts the bounded inline core as the explicit last resort with stats accounting. Bench (bench/open-lifecycle, seed 42): event-loop delay max across the four open scenarios drops from 45/734/331/492 ms to ~12-28 ms with wall time flat or better. * feat(kap-server): run the global search index in a dedicated worker Move the whole search-index MiniDb lifecycle (open, generation load, WAL replay, sync, rebuild, compaction) off the main thread into a long-lived worker_threads host, so it never shares the event loop with TUI input: - Add a versioned request/response protocol and worker entry hosting a host-agnostic SearchIndexCore; the same core also backs an inline backend kept as the explicit rollback (KIMI_CODE_EXPERIMENTAL_SEARCH_WORKER=false, flag default ON). - The worker exclusively owns the search-index handle. The lock token is reported at acquire time (new MiniDb OpenOptions.onLockAcquired hook) and reaped on dirty exit; an orphan-lock detector (same-pid lock row whose token no live holder owns) recovers the window where the token report is lost, so a mid-open crash can never freeze the index into a silent permanent read-only. - Crash handling: in-flight requests are rejected with typed errors, respawn uses capped exponential backoff, per-request watchdogs terminate wedged workers, and beginClose propagates into the worker so dispose stays bounded during a long sync. Page tokens pin a boot-salted generation, so tokens issued before a transparent worker restart fail closed with invalid_page_token. - The main process keeps the sync coordinator (debounce/coalescing/ single-flight), live transcript routing, query normalization and page-token codec; searches keep reading the published generation and report building/stale/degraded instead of waiting for sync/rebuild. - Wire the worker into the CLI packaging: self-contained worker bundles for npm dist and the SEA asset manifest/installer/smoke check, plus a dev runtime (type-stripping + .ts resolve hook) scoped to worker execArgv. * feat(kap-server): model search and session-index lifecycles explicitly Consolidate the two-index separation into explicit, diagnosable lifecycles: - Surface the global search state machine (stopped / opening / building / ready / degraded / closing) end to end: SearchIndexCore.lifecycleState, SearchWorkerHost lifecycle snapshots cached from RPC responses (and invalidated across worker generations), a never-throwing status() carrying the lifecycle, and a synchronous lifecycleReport() that neither kicks the open nor spawns the worker. Corrupt search-index rebuilds are announced with a dedicated warn log so building, stale, degraded, corrupt and worker-unavailable stay distinguishable. - Turn MiniDb read-only replica catch-up fully cooperative: catchUpWalAsync scans frames with the windowed async scanner and yields per primitive op on the shared walApplySlicer budget, while a per-instance catchUpChain serializes concurrent catch-ups so each caller keeps its atomic watermark advance. The stale synchronous implementations are removed. - Pin the dependency direction and availability timing with tests: session list/create/resume survive a corrupt or unopenable search index (also end-to-end with a dead query-store), search generation reuse and stale-serving keep working across restarts, concurrent cold callers open the index / spawn the worker exactly once, resume-then- fetchSessions performs no duplicate authoritative scan, and a clean dispose releases the lock and settles at stopped. - Document the experimental flag surface (persistence_minidb_readmodel, search_worker) in the root guide. * feat(agent-core-v2): default the session read model on and roll out the separation Rollout and validation for the index separation plan: - Flip persistence_minidb_readmodel to default ON (rollback via KIMI_CODE_EXPERIMENTAL_PERSISTENCE_MINIDB_READMODEL=false or the experimental config section); session list/--resume/--continue now always go through the isolated session read model with the authoritative fallback. Test harnesses pin the flag off where shared fixtures require hermetic homes, while the dedicated suites keep explicit on/off coverage. - Add a probe proving the main thread stays responsive while the search worker rebuilds and swaps a generation (reindex), completing the TUI responsiveness matrix. - Record the rollout state in the agent-core-v2 guide (session index section) and the root flag line. - Add changesets for the CLI (worker isolation, session index independence) and minidb (cooperative open lifecycle). Validation: full suites green across minidb (551), agent-core-v2 (4760), kap-server (1005), node-sdk (343), klient (91) and the CLI app (2567); open-lifecycle bench event-loop delay max is down from 45/734/331/492 ms to ~16-22 ms across the four scenarios with wall time flat or better. * fix(agent-core-v2): evict deleted sessions from the mirror queue and drain the index on close Two issues surfaced by the read-model default in the acp-server suite: - ISessionIndex.remove only deleted from the query store, but a summary still queued in the mirror was folded back into reads (and re-written by the next flush), resurrecting a deleted session in listings. The mirror now exposes evict(id): drop the queued summary and wait out an in-flight flush before the store delete. - RunningAcpServer.close and SDKRpcClientV2.close disposed the engine without awaiting the asynchronous mirror flush / query-store close, so a host removing homeDir right after close() raced in-flight shard closes (ENOTEMPTY). Both now follow the kap-server shutdown order: drain the mirror while the store is open, dispose, then await the drains. * fix(minidb): pause active expiry during the sliced bulk load The store's active-expire timer is armed at construction, so during a sliced bulkLoadRefsAsync a tick can fire mid-load: it reaps a TTL key from the map while the order skiplist is still the old empty one, and the final bulkLoadAsync then rebuilds order from the stale orderEntries snapshot — resurrecting the expired key in the ordered index (and duplicating it if the key is later set again). The sync bulkLoadRefs had no yield windows, so guard the async path with a bulkLoading flag that defers expiry ticks until the load settles (finally-safe). * chore: consolidate changesets into the TUI startup freeze fix	2026-08-07 07:38:16 +08:00
qer	335588e259	feat(agent-core-v2): persist the last turn outcome into session metadata for cold listings (#2666) ... * feat(agent-core-v2): persist the last turn outcome into session metadata for cold listings A cold session (no live handle) reported no lastTurnReason, so after a server restart the session list could not mark a session whose last turn failed until it was opened and resumed. A new Session-scope SessionOutcomeRecorder subscribes to the activity aggregate's turn_ended changes and persists the outcome (completed/failed) into the session metadata document; the summary pipeline (mirror + cold reader) carries it as SessionSummary .lastTurnReason, and toWireSession falls back to it when no live fact exists. 'cancelled' is deliberately not persisted: it is also what an in-flight turn ends with during scope disposal, and writing there races the host's home-dir teardown. Verified end to end with an isolated home and a dead provider: a turn fails, the server restarts, and GET /sessions reports last_turn_reason=failed without opening the session. * fix(klient): carry lastTurnReason/lastTurnOutcome in the validated contracts Review follow-up: zod strips unknown keys on parse, so the new outcome fields never reached klient callers; add them to the session summary and metadata/patch/key schemas (contract parity test covers the engine mirror). * fix(agent-core-v2): persist user-cancelled outcomes, never teardown aborts Review follow-up: skipping every 'cancelled' left a stale earlier outcome in the metadata (e.g. a prior failed reported for a session whose latest turn was stopped by the user). The recorder now subscribes to the main agent's turn.ended facts directly and keys on interruptReason: user_cancelled is persisted like any other terminal state, while programmatic aborts — including the cancel every in-flight turn suffers during scope disposal — are never written, so no metadata write races the host's home-dir teardown. * fix(kap-server): only fall back to the persisted outcome for cold sessions Review follow-up: a warm session that just started a new turn clears its live lastTurn, and the unconditional ?? fallback would then report the previous turn's persisted outcome for a turn that is still running. SessionFacts now reports whether a live handle exists, and the wire projection only reads the persisted value when the session is cold. * docs(agent-core-v2): keep the outcome-recorder header at role level * fix(agent-core-v2): settle turn outcomes on turn start and drain metadata writes on close Review follow-ups: - a new main turn now clears the persisted outcome (turn.started), so a process that dies mid-retry no longer reports the previous turn's terminal state for a turn that never ended - the dedupe marker only advances after a successful write, so a failed persist no longer suppresses the next identical outcome - session metadata writes are tracked in a module-level pending set with drainSessionMetadataWrites(), awaited by kap-server close alongside the mirror/query-store drains — an event-driven write (e.g. the outcome recorder) can no longer land in a session dir while the host removes it * fix(agent-core-v2): track the metadata dispose flag locally Disposable exposes no public isDisposed accessor; keep a class-local flag set in the dispose override. * fix(kap-server): drain session metadata writes before the mirror and disposal A write still in flight when close() begins must settle before the mirror flushes its summary into the read model and before scope disposal marks the service disposed — not after. * fix(agent-core-v2): reattach the recorder when the main agent is recreated Review follow-up: a failed bootstrap still fires onDidCreate before the handle is dropped; the subscription then pointed at a dead bus and the guard blocked any later reattach. Track onDidDispose and reset so the next main creation attaches cleanly. * test(agent-core-v2): resolve the recorder through the scoped DI harness Review follow-up: construct SessionOutcomeRecorder via registerScopedService + a Session-scope test host (stubbed lifecycle/metadata), so the test covers the production registration path; add the durable-value adoption case. * fix(agent-core-v2): unbreak CI — iterable Promise.all and the debug channel surface - Promise.all takes the pending-writes set directly (oxlint error) - the disposed flag moves into a _register'd marker instead of a public dispose() override, which the debug channels listing (and its test) correctly rejects as framework plumbing * fix(kap-server): surface persisted failures on the v2 session status The v2 list folds the outcome into activity.status, which previously read only live facts — a cold session always looked idle. Cold sessions now map a persisted failed outcome to status 'failed' (completed and cancelled stay idle, matching the live fold); warm sessions are unchanged, and the statuses filter inherits the mapping. * refactor(agent-core-v2): name the persisted field lastTurnReason Aligns with the established name for the same concept end to end (activity view's lastTurnReason, the v1 wire's last_turn_reason, and the SessionSummary mirror), instead of introducing a third variant. * fix(agent-core-v2): drain pending metadata writes before session teardown Review follow-up: closing/archiving a session right after a turn ended could dispose the scope while the outcome write was still queued, and delete() removes the session dir immediately after close. Await the pending metadata writes before the handle goes away. * fix(node-sdk): carry lastTurnReason through the SDK session summary Review follow-up: the in-process SDK path maps the engine summary through v2SummaryToSessionSummary, which dropped the new outcome field. Add it to the public SessionSummary type and the mapper; the parity gate projects it away (the v1 engine never records an outcome). * fix(node-sdk): populate lastTurnReason on live SDK summaries Review follow-up: resumeSession/reloadSession build their summary from the live session's metadata document, which now carries the outcome — surface it there too so the SDK reports it consistently for live and listed sessions. * fix(agent-core-v2): carry the last turn outcome across session forks Review follow-up: fork skips state.json when copying the session dir, so the fork's fresh metadata never had the outcome and a restart dropped a marker the warm fork was still reporting. The fork's metadata patch now inherits the source's lastTurnReason. * fix(agent-core-v2): settle pending outcome writes before reading a fork source Review follow-up: a fork requested right after the source's turn ended could read the metadata before the recorder's queued write landed, inheriting a stale or absent outcome. Drain pending metadata writes first. * fix(agent-core-v2): backfill restored outcomes into the session metadata Review follow-up: for sessions whose last turn ended before this field existed, the cold-resume seed restores the outcome into the activity view without a turn.ended fact, so the recorder never persisted it and cold listings stayed blank. The recorder now also watches the main agent's activity updates and backfills the restored outcome when nothing is persisted yet. * fix(agent-core-v2): never backfill restored cancellations Review follow-up: a restored 'cancelled' cannot be told apart from a programmatic abort (the activity event carries no interruptReason), and those are never persisted. Backfill now covers only completed/failed; user stops are still persisted from the live turn.ended fact. * refactor(agent-core-v2): rename the outcome recorder to outcome mirror Mirror is the codebase's established term for a write side that reflects live state into a store (SessionIndexMirror); Recorder has no precedent. * fix(agent-core-v2): backfill without bumping recency; header-only comments Review follow-ups: - a mere resume must not float an old session to the top of the list: metadata updates accept touchUpdatedAt:false and the outcome mirror's backfill uses it (live outcome writes keep bumping — turn end is a recency moment) - the mirror service's inline notes move into the file header per the package comment convention - drop the redundant |undefined from the SDK's optional outcome field * fix(node-sdk): read the live outcome for resumed session summaries Review follow-up: on a fresh resume the restored outcome can still be queued as a metadata backfill, so the document may lag a tick; the live activity aggregate already holds it. Resume/reload summaries now prefer the live value and fall back to the metadata field. * fix(agent-core-v2): confine the outcome backfill to pure resumes Review follow-up: the view publishes its turn.ended fold before this mirror's own turn.ended handler runs, so a live ending reached the backfill branch first and got persisted without the recency bump. The backfill now only applies when no turn ever started in this process — live endings always take the bumped write. * fix(agent-core-v2): drain the session-index mirror before session teardown Review follow-up: settling the metadata write alone left the fresh summary in the mirror's pending queue, so a list right after close could read a stale outcome from the read model. close/archive now also drain ISessionIndexMirror. Test harnesses register a mirror stub for the new dependency. * docs(agent-core-v2): fold the metadata drain contract into the file header * chore: include the SDK package in the changeset; fold the drain note into the header * fix(agent-core-v2): backfill restored cancellations too, quietly Review follow-ups: dropping every restored cancel loses legitimate user stops whose live write never landed (or was rejected) before a restart — cold surfaces never mark cancelled anyway, so healing them is harmless and strictly more accurate. The metadata disposal note moves into the file header per the comment convention. * fix(node-sdk): prefer the live outcome over the index in SDK listings Review follow-up: a live session that just started a new turn after a failure can briefly keep the stale outcome in the index while the mirror's clear is queued. listSessions now reads the live activity aggregate for warm sessions, matching the kap-server cold-only fallback. * fix(node-sdk): never read the metadata outcome for a live session Review follow-up: with a retry in flight the live aggregate has no outcome while the document may still hold the previous failure — the fallback showed the stale one. Live summaries now take the live aggregate's answer alone; the restored outcome is already seeded there on resume.	2026-08-06 20:14:05 +08:00
Haozhe	02c026d487	feat(agent-core-v2): tombstone removed MCP servers and freeze plugin prompt inputs (#2694) ... * feat(mcp): tombstone removed MCP servers and apply plugin changes immediately (20 files) - add 'removed' MCP server status: workspace config removals call markRemoved instead of remove, keeping tool registrations alive while short-circuiting calls with a removal notice - fire onDidReload after every plugin mutation (install/enable/disable/remove) so workspace consumers refresh contributions immediately - TUI renders the removed status in the MCP panel/startup summary and shows an apply-immediately hint on the v2 engine * feat(agent-core-v2): freeze plugin prompt inputs for live agents (2 files) - snapshot the model skill listing and plugin system-prompt sections on the first successful prompt build and reuse the frozen values for the agent's lifetime, so plugin install / enable / disable / remove / reload never rewrites a live agent's prompt (same keep-live-sessions-stable philosophy as the MCP tombstone) - freeze only on success: a not-yet-ready skill catalog or a failed enabledSystemPrompts() read must not pin empty values for the agent's lifetime - refreshSystemPrompt still rebuilds on catalog change events but reuses the frozen values, so the prompt only moves when non-plugin inputs change (AGENTS.md, [tools] section, session tool policy, compaction); new agents snapshot the then-current state * chore(changeset): add changesets for MCP tombstone and frozen plugin prompt inputs * docs: describe immediate plugin changes and the removed MCP status on the v2 engine * fix(klient): mirror the removed MCP server status in the wire contract * docs: drop the legacy-engine behavior notes from the plugin and MCP pages * fix(agent-core-v2): freeze plugin sections only on a loaded snapshot - enabledSystemPrompts() resolves to its consumption fallback (never rejects) while the initial plugin load has failed; freezing that empty read locked plugin sections out of the live agent even after a later successful reload - expose hasLoadedSnapshot() on IPluginService so resolvePluginSections can tell a real empty snapshot from the fallback before freezing	2026-08-06 19:19:51 +08:00
liruifengv	cfd14a1fe2	feat(kap-server): accept attachments on skill activation (#2693) ... * feat(kap-server): accept attachments on skill activation The :activate endpoint only took {args?}, so REST clients (web/desktop composers) could not attach uploads to a /skill invocation — attachments were silently dropped at the edge. - activateSkillRequestSchema gains an optional attachments field carrying the image/video/file subset of the prompt content wire shape. - The skills route resolves them through the same edge pipeline as prompt submissions (validate file refs → materialize/compress → convert), extracted from routes/prompts.ts into lib/promptMedia.ts. - AgentSkillService.activate appends the resolved parts after the rendered skill prompt in the activation's user message; SkillActivationInput gains an optional content field. The native RPC/TUI path is unchanged. - Attachment failures map to 40407 file.not_found / 40001 validation.failed, mirroring the prompts route. * fix(kap-server): drop the unused parseKimiFileUrl import in promptMedia * refactor: address review — header-only comments in the skill domain, provider id on protocol URL sources - agent-core-v2 keeps comments solely in the top-of-file block (scoped guide): SkillActivationInput.content documented in the skill.ts header, the activate() note folded into the skillService.ts header. - packages/protocol's image/video URL source gains the optional provider-issued id, matching the kap-server wire schema so parsing the public contract no longer strips it. * fix(kap-server): validate the skill before materializing activation attachments An unknown or non-user-activatable skill name with attachments ran the media pipeline first, streaming bytes into the session/cache dirs and compressing images for a request that activate() would reject with 40415/40912. The route now checks the session catalog up front (the service still re-validates) so invalid activations leave no disk or CPU side effects.	2026-08-06 19:09:32 +08:00
Haozhe	8c766a6c30	feat(agent-core-v2): add the L3 unit layer and the Feature seam (#2678) ... * feat(agent-core-v2): add the L3 unit layer and the Feature seam - introduce the L3 Service/Fiber unit layer: the Service base class with this.provide/effect/on/get/ref capabilities, the fiber runtime with thenable FiberHandles, collection contribution points, and the per-scope-kind ScopeUnits materialization fold - provide each scope's static registration batch as one atomic provideAll cascade transaction (waiting-area activation, sticky Failed on construction error) - add the DI unit inspection surface: App-scope debug ledger / dependency graph / cascade history services and the kimi-inspect DI view - add the Feature unit seam (IFeatureManager + feature assembly), port plan mode onto it, and add the contributed-command seam (agent-command domain + node-sdk RPC types) - remove the legacy dep-graph tooling - apply the header-only comment convention across src and test: strip non-header narration, keep the file header, tooling pragmas, and NOTE comments * feat(kap-server): gate the event.di.* debug feed to kimi-inspect connections - add an opt-in target set in SessionEventBroadcaster; the global fan-out now skips event.di.* frames for connections that never opted in, so kimi-web and other clients no longer receive the high-churn DI feed - WsConnectionV1 opts a connection in when client_hello carries client_id 'kimi-inspect'; removeGlobalTarget drops the opt-in on close - temporary gate until a client-declared event-type whitelist lands * chore(agent-core-v2): fix oxlint errors in the DI unit layer - build the live-ref container chain without aliasing this (no-this-alias) - snapshot the materialized map with Array.from and document why the copy is required (no-useless-spread) * test(klient): use string scope kinds in the lifecycle handle fakes The engine's LifecycleScope is a string enum now; the facade test doubles still returned the old numeric kinds and failed the handleWireSchema output validation. * build(nix): update the pnpmDeps fetch hash	2026-08-06 18:22:36 +08:00
liruifengv	7b2784b9b7	feat: surface the bound model and thinking effort on subagent UIs (#2679) ... * feat: surface the bound model on subagent UIs The subagent.spawned event now carries the display-normalized model alias (the derived __secondary__ entry resolves to its base alias), so clients can show which model a subagent is bound to. The TUI subagent card, swarm panel header, and background-agent entry show it at spawn; the WS snapshot roster and REST /tasks (background/detached subagents) carry it too, keeping the model visible across client reconnects. * feat: carry the subagent thinking effort alongside the model The spawned event, snapshot roster, and REST /tasks now also carry the child's effective thinking effort (read from the child profile at spawn, the same vocabulary as agent.status.updated). UIs show it only when it diverges from the main session's current effort — an inherited level adds no information, and 'off' is never shown. * feat(tui): show the bound model and effort in the /tasks browser The task browser's Detail pane renders Model and Effort rows for agent tasks (raw alias and level — it is the inspector surface, so no diff filtering), and its minimum height grows to fit the new rows. The values were already persisted on SubagentTaskInfo; the TaskInfo union, its zod schemas (protocol, kap-server, klient contract), and the v1 type declaration now carry them so nothing strips them in transit. * feat(tui): show concrete subagent effort levels unconditionally Display rule simplified: any concrete effort tier (low/high/max/…) is shown next to the model — including when it matches the main session's level. Only the boolean states stay hidden: 'off' (no thinking) and 'on' (generic thinking) carry no level information. * docs: trim the changeset entry * fix(tui): keep the model and effort on background-agent entries across resume replayBackgroundProjection only copied agentId/parentToolCallId/ description, so a background subagent that outlived a resume lost its model/effort on the later terminal transcript entry. The projection now threads the persisted values (catalog-mapped model; boolean effort states dropped), and session replay passes the loaded model catalog through. * fix(agent-core-v2): normalize the derived secondary alias regardless of the flag A child bound while the secondary-model experiment was on keeps __secondary__ in its persisted binding; if the flag is later switched off with the recipe still configured, resolveSecondaryModel() gated the normalization and the sentinel leaked back onto resumed subagents. subagentDisplayModel now reads the recipe straight from config (the flag gates new bindings, not the interpretation of existing ones), which also drops SessionSwarmService's now-unused IFlagService dependency. Also adds the SDK package to the release: the new SubagentSpawnedEvent/AgentTaskInfo fields are SDK-visible types. * fix(agent-core-v2): normalize the status-frame model at the source A derived-bound child republishes agent.status.updated right after spawn with its raw modelAlias, which overwrote the spawned event's normalized display model on single-subagent cards (swarm headers were first-wins and escaped). emitStatusUpdated now maps through subagentDisplayModel, a no-op for the never-derived main agent. Also moves the inline comments added by this branch into top-of-file headers per the v2 comment convention. * fix(tui): clamp the /tasks detail frame to the available body At terminals near the minimum height the forced 10-row detail frame overflowed the body and truncated the preview frame's border. The detail height now caps out at whatever leaves the preview its borders plus one content row, with a regression test at exactly MIN_HEIGHT. * fix: normalize inherited derived aliases and keep model/effort on replayed terminal entries - resolveSubagentBinding's caller-fallback branch also maps through subagentDisplayModel: a caller itself bound to the derived entry (a resumed subagent making a nested Agent call) no longer publishes __secondary__. - The replayed background-task terminal notification builds its metadata with the persisted model (catalog-mapped) and concrete effort, matching the live completion path. - Drops the inline comments this branch added inside v2 test bodies; the scenario context lives in the source file headers.	2026-08-06 16:59:45 +08:00
Haozhe	2b893733f9	fix(kap-server): bypass Node arg quoting for explorer /select, on Windows (#2645) ... explorer.exe parses its raw command line rather than argv, so Node's default spawn quoting breaks the `/select,` argument whenever the path contains spaces: the command line becomes `"/select,\"C:\...\""`, which explorer rejects, silently opening the Documents folder instead of selecting the file. Quote only the path portion and launch with windowsVerbatimArguments so the command line keeps the documented `/select,"C:\some dir\f.txt"` form.	2026-08-05 20:15:27 +08:00
Haozhe	510fbe7ec5	refactor(kap-server): wrap /api/v2/sessions in the v1 response envelope (#2644) ... - return the domain-grouped page payload inside { code, msg, data, request_id } and carry business outcomes in code (40001 invalid params with details, 40922 page_token mismatch) instead of raw HTTP statuses plus an { error: { code, message } } body - add ErrorCode.PAGE_TOKEN_MISMATCH (40922) - register the route via defineRoute (shared runtime validation and envelope-wrapped OpenAPI docs); fold include-domain validation into the query schema and replace the preprocess/doc-twin pair with scalar-or-array union params - update the kimi-inspect client to unwrap the envelope and sync the two AGENTS.md guides	2026-08-05 18:20:00 +08:00
Haozhe	6f1cd7ca22	feat: add v2 sessions API and spreadsheet-like session table in kimi-inspect (#2640) ... - kap-server: add GET /api/v2/sessions with a domain-grouped response (workspace / meta / activity, opt-in git), status / archived / updated_after filters, three sort orders, and fingerprint-bound opaque cursor pagination - kimi-inspect: rebuild the chat sidebar as a spreadsheet-like session table on the v2 endpoint — preset views (All / Opened / Archived / By workspace / Git), column visibility config, header sort toggles, cursor-paged Load more, and localStorage-persisted panel prefs - live activity frames from the WS hub override the REST status badge; session created / meta-updated events invalidate the v2-sessions query	2026-08-05 17:28:11 +08:00
Haozhe	2a4990182d	docs: slim root AGENTS.md, move deep package docs to package guides (#2626) ... - move the kimi-inspect, kap-server, transcript, and minidb project-map entries into new package-level AGENTS.md files - move the standalone Agent class rule to packages/agent-core/AGENTS.md - merge root-only agent-core-v2 facts (MCP persistence, trust routes, seed contract examples) into packages/agent-core-v2/AGENTS.md - compress the remaining long project-map entries to summaries with pointers, and add an anti-bloat rule for map entries - drop the stale server-e2e entry; the package no longer exists	2026-08-05 13:43:33 +08:00
Kai	98ee35afd2	feat(agent-core-v2): add custom agent identity (#2573) ... * refactor(agent-core-v2): simplify context tags and shared copy Rename the context-injection tags to `<skill-loaded>` and `<plugin-instructions>`, drop the product prefix from the CronCreate tool description and the default agent description, and point the MCP OAuth callback page back to "your terminal" instead of naming one client. The callback page is shared by the ACP host, the web UI, and embedding hosts, so naming a single client was inaccurate there. The tags and the two descriptions read exactly the same without the prefix. Verified no runtime consumer matches the old tag names; the updated snapshots cover the tool descriptions that changed. * feat(agent-core-v2): add a switch for the product-documentation skills Five builtin skills document this CLI itself — `update-config`, `custom-theme`, `mcp-config`, `check-kimi-code-docs`, and `import-from-cc-codex`. Their names and descriptions sit in the system prompt on every turn, which is dead weight for runs that will never reconfigure the CLI. Add a top-level `builtin_product_skills` field (also settable through `KIMI_CODE_BUILTIN_PRODUCT_SKILLS`) to drop them. On by default, so nothing changes unless it is set; the trade when off is that the model loses the guided flows for those tasks. Filtering happens where the catalog is assembled — a later filter would leave the skills advertised to the model. The whole section is one scalar, so it exercises the section-level env binding branch and needs its own strip: `stripEnvBoundFields` only walks object fields, so an env override would otherwise be written back into `config.toml`. * feat(agent-core-v2): add custom agent identity Add an `[identity]` config section (`name`, optional `slug`, both also settable through `KIMI_CODE_IDENTITY_NAME` / `KIMI_CODE_IDENTITY_SLUG`) that sets the identity the agent presents: the name it calls itself in the system prompt, the `User-Agent` product token sent to third-party providers, and the client name announced to MCP servers. Leaving it unset changes nothing. Until now every one of these was fixed, which left no way to run the agent as part of another product — an internal deployment, a fork with its own branding, an embedding host. The identity resolves inside the engine rather than being seeded by each host, so it applies to every launch surface — including headless runs, which today seed no display name at all and fall through to the built-in default. Two deliberate asymmetries: - The display name is a filling value with a fallback chain (config > host-declared > the consumer's own default); the slug is a rewriting value with two states only, so with no identity configured the rewriting paths are equivalent to not existing. - The rewrite happens in the outbound header assembly, the one layer that knows which vendor it is building for. Vendors declaring `hostHeaders: 'full'` keep the host's own product token, which that header set is built around and which backends key on; the configured identity applies to the third-party path. Resolution is lazy throughout: config loads asynchronously, and a constructor snapshot would freeze the pre-load value under some startup orderings. Two input edges the resolver has to absorb, since both would otherwise reach the User-Agent builder and either break it or quietly rewrite the header: blank and whitespace-only values read as unset in the file just as they already did in the env, so a stray `name = ""` cannot claim an identity; and a name that folds away to nothing under slug normalization (a CJK-only name, say) falls back to a neutral token rather than producing a blank product, which the builder rejects. * fix(agent-core-v2): keep the file value when a scalar env binding fails to parse `config.ts` documents that an env value failing its binding's `parse` is ignored, and `applyEnvBindings` honors that for object fields by assigning only when the resolved value is defined. `applySectionEnv` returned the parse result straight through for whole-section scalar bindings, so a blank or mistyped variable resolved to `undefined` and cleared the configured file value instead of being ignored. Nothing hit this before: every existing section either binds object fields or is env-only. `builtin_product_skills` is the first whole-section scalar binding, where exporting an empty or misspelled `KIMI_CODE_BUILTIN_PRODUCT_SKILLS` would silently undo a configured `false`. * feat(agent-core-v2): extend the custom identity to discovery and global MCP Two outbound paths still announced the built-in product name under a configured identity: - `DiscoveryService` read the host User-Agent straight from bootstrap args when refreshing provider models, so custom registries — which are third-party endpoints — saw the original token while chat requests to the same class of endpoint saw the configured one. - `SDKRpcClientV2` builds its own global `McpOAuthService` plus a throwaway `McpConnectionManager` for server testing, neither of which goes through the workspace-owned manager that carries the resolver. Both now resolve the identity from the App scope. * refactor(agent-core-v2): neutralize remaining copy and align comments The synthetic MCP authentication tool description is injected into the model context and still named the product; it and the OAuth callback pages now use client-neutral wording. "Return to your terminal" was no improvement over naming a client — both assume what the host is, and that page serves the ACP host, the web UI and embedding hosts alike. Comments introduced by the identity work move into their module headers, per the domain convention. Interface field docs stay: the rule names functions, methods and statements, and field-level docs are established across the codebase. The new tests gain scenario headers and dispose the scoped hosts they create, and the `[identity]` docs state which engine reads the section. * fix(agent-core-v2): read the product-skill switch after config is ready `BuiltinSkillSource` is the lowest-priority skill source, so the workspace catalog loads it first — before `IConfigService` has finished loading — and keeps the contribution it returns for the life of the handler, with no reload path and no change event. Reading `builtin_product_skills` eagerly therefore stranded the startup configuration: an explicit `false` could be ignored for the whole process. `UserFileSkillSource` already awaits config readiness for exactly this ordering; this source now does the same. Also record the identity collaborator in the two module headers that gained the dependency without documenting it, and scope the `builtin_product_skills` docs to the engine that reads it, matching the note the identity section already carries. * fix(agent-core-v2): apply the product-skill switch to session-less listings `builtin_product_skills = false` only reached the scoped skill source. The SDK's `listWorkspaceSkills` and the server's `GET /workspaces/{id}/skills` both composed the raw `BUILTIN_SKILLS` constant, and the web app feeds its pre-session onboarding menu from that route — so the five product skills stayed listed until a session existed, then vanished from the session's catalog. Move the decision into `visibleBuiltinSkills(enabled)` next to the constant and route every consumer through it, reading the switch via the shared `builtinProductSkillsEnabled`. Keeping "what counts as a product skill" in one place is the point: three copies of the predicate would drift the next time a builtin is added. The SDK listing also awaits config readiness, which it did not do before. * fix(node-sdk): await config before materializing the global MCP OAuth provider `McpOAuthService` caches providers by store key and stamps the client name when it first builds one, and the preceding `globalMcpConfig.get()` reads `mcp.json` directly rather than through `IConfigService`. So a `beginGlobalMcpServerAuth` call made right after the harness is created could resolve the identity before config finished loading, pinning the built-in label for the rest of the process — including the OAuth dynamic registration a third-party MCP server records. `testGlobalMcpServer` already awaited config readiness for its own reasons; this path now does too. * refactor(agent-core-v2): drop the unused builtin-skill registrar `registerBuiltinSkills` stamped the raw constant into a catalog for "edge composition without a Session" — exactly the shape that now has to respect `builtin_product_skills`. It has no callers in v2 and is not exported from the package index, so it was dead code that also stood as an invitation to bypass the switch. v1 keeps its own copy. Every remaining path composes builtins through `visibleBuiltinSkills`. * fix(agent-core-v2): send the configured identity on custom-registry imports `:import_registry` fetched a user-supplied third-party URL with a hardcoded `kimi-code-kap-server` User-Agent, so the first request to a registry announced the product while every scheduled refresh of the same registry announced the configured identity. The hardcoded value was wrong on its own terms too: that token names the server, and this path also runs in the CLI. Both services now project the identity through `identityUserAgent`, which carries the two guards (no host header, or no identity) once instead of per caller. The model catalog keeps an inline copy on purpose — kosong is a foundational layer and must not import an app domain. Sweeping the remaining outbound User-Agent sources found no further gaps: WebFetch deliberately sends a Chrome-like UA, the models.dev catalog fetch sends none from the CLI, and kap-server's `user-agent` reads are inbound. * docs: scope the identity env vars and condense the changeset The environment-variable reference advertised all three new variables without noting that only the agent-core-v2 engine reads them; the configuration page already carried that note. Added in both locales. The changeset had grown into two paragraphs of implementation detail, which is what would land in the CLI release changelog. `gen-changesets` asks for one short sentence plus at most a one-line usage hint. * docs(agent-core-v2): describe the identity as what the agent calls itself The module headers had drifted into describing the feature by what it keeps off the wire rather than what it configures. Reworded so they state the capability: the identity is the name the agent uses for itself, and the unset case is a no-op rather than something "safe". The product-skill switch excludes skills rather than hiding them. Wording only; behavior and structure unchanged. * test(agent-core-v2): cover the identity on custom-registry imports The import path switched from a hardcoded `kimi-code-kap-server` token to the host User-Agent projected through the identity, but nothing asserted it. Two cases pin both halves: a configured identity reaches the request, and an unconfigured one leaves the host header intact — the second matters because a single case would also pass if one hardcoded value had simply replaced another. Both fail against the previous implementation. * fix(node-sdk): guard every global MCP OAuth path behind config readiness `McpOAuthService` caches providers by store key and stamps the client name when it first builds one, so any path that can materialize a provider has to run after config has loaded. `beginGlobalMcpServerAuth` awaited readiness, but `resetGlobalMcpServerAuth` reaches the same cache through `invalidate()` -> `getProvider()` without waiting: resetting auth right after the harness is constructed pinned the built-in client name, and the await added to the begin path could not help because it then reused that cached provider. Rather than add the missing await, the accessor is now async and holds the guard itself, so the service cannot be obtained before config is ready and a future entry point cannot forget. The remaining `configReady` in `testGlobalMcpServer` stays — that one is for its own `[mcp]` section read. * fix(agent-core-v2): send the configured identity on models.dev requests The directory fetch behind `listModelsDevProviders` / `getModelsDevProvider` still hardcoded a `kimi-code-kap-server` User-Agent, so browsing or importing from models.dev announced the built-in product — and claimed to be the server even when running in the CLI. Only the custom-registry import had been fixed. `getModelsDevCatalog` now takes the User-Agent from its caller: the module is plain module-level state with no container access, and the value depends on the host and the configured identity, which only the calling service can see. All four third-party fetches in that service share one helper. Where the host states no User-Agent, a neutral token stands in rather than dropping the header — these are directories the service chooses to call, so there is no host intent to preserve, unlike the provider requests the model catalog assembles. Both new tests fail against the previous hardcoded value. * test(agent-core-v2): assert the product-skill set literally The expected sets were derived from the same `productSpecific` field the production filter reads, so a builtin silently losing its marker would just move between sets and leave every assertion green — while staying visible to the model once the switch is off. The five names are now literal, with a test asserting the marked set matches them exactly. Dropping the marker from one skill now fails four tests instead of none. Also states the App scope in the identity contract header, per the domain's comment convention for contract files. * fix(agent-core-v2): normalize the host-declared display name too Blank and padded values were normalized on the config side but not on the host fallback, so an embedding host passing `displayName: " "` rendered "You are ," into the system prompt, and a padded name kept its padding. Same rule now applies to every source of the name. Also names `agentIdentity` as the collaborator in the request-headers adapter header, which described the value it obtains without saying which domain resolves it. The three new cases fail against the previous implementation. * fix(agent-core-v2): keep the configured slug when the host sends no User-Agent The neutral fallback added for hosts that state no `User-Agent` discarded a configured identity along with it: `identityUserAgent` returns `undefined` as soon as there is no host header to rewrite, so `?? DEFAULT_IDENTITY_SLUG` sent the literal `agent` even when `[identity].slug` was set — precisely the case that fallback exists to serve. The configured slug now stands on its own, with the neutral token reserved for having neither. The four combinations of (host header, configured slug) had three tests; the missing one is the one that was wrong. It now fails without this change. `outboundUserAgent` also awaits config readiness before reading the identity, so a browse issued right after bootstrap cannot send the pre-load value — the guard lives in the accessor rather than at its four call sites, matching how the same race is handled elsewhere in this branch. Both headers here and in `discoveryService` now name `agentIdentity` as the collaborator resolving that token. * test(acp-server): follow the renamed skill-activation tag `acp-server` arrived on main after the tag rename, so its two assertions still expected `kimi-skill-loaded` and failed once the branches met. Also updates the web app's CSS comment, which named the old tag from the start of this branch — a comment, so nothing ever failed on it. Found by CI: the merge verification only ran agent-core-v2's suite, and this package is neither a dependency nor a dependent of it. * fix(agent-core-v2): present the configured slug on registry refreshes too The previous round taught the import path to fall back to the configured slug when the host states no `User-Agent`, but left the scheduled refresh of the same registry on the bare projection — so one registry could see `acme` on import and the runtime default on refresh. Extracting `identityUserAgent` had made the two paths share a function without sharing the policy. The choice itself is now the shared piece: `identityUserAgentOrDefault` always yields a value, for the directories this process chooses to call, while `identityUserAgent` stays the form that rewrites only what the host already sends — what a provider request needs, where the host's silence is its own choice. * docs(agent-core-v2): move new member docs into the module headers The domain's comment convention is absolute — comments live solely in the top-of-file block — and I had read the "functions, methods, or statements" clause as leaving interface members out. It does not: only 25 of 734 v2 sources carry an indented block, so the members I documented were the exception, not the pattern. Seven members across six files move into their headers. `types.ts` had no header at all, so it gains one. * fix(agent-core-v2): connect session MCP overlays after config is ready The shared manager reaches `connectAll` through `initialize()`, which awaits the config domain first; `sessionOverlay` called it straight away. A session carrying ephemeral `mcpServers` created right after bootstrap therefore resolved the client name before config had loaded and initialized under the built-in one. The blast radius is wider than that one connection: a remote server sends the overlay through `hasTokens()`, which materializes an OAuth provider on the *shared* service and caches it by store key — so the early name outlives the connection that raced. The overlay now connects behind `mcpConfig.ready`, leaving the returned readiness promise unchanged. * fix(agent-core-v2): reload builtin skills when their switch changes The workspace catalog keeps each source's contribution for the life of the handler, so a `builtin_product_skills` toggle never reached an existing handler's sessions. That was harmless while every surface read the same constant — but routing the session-less listings through the config made the two views disagree, since those read the switch on every call. Follows `ExtraFileSkillSource`: subscribe to the owning section and fire `onDidChange`, which the catalog already turns into a source reload. The test asserts an unrelated section does not trigger it. * fix(agent-core-v2): apply the identity to self-configured web services `[services.moonshot_search]` and `[services.moonshot_fetch]` name their own `base_url`, so both services can point at an endpoint the user chose — but each forwarded the host request headers verbatim, sending the built-in product token there under a configured identity. Only the services-config path is rewritten; the managed OAuth path keeps the host headers as they are, being the endpoint the session authenticated against. The distinction is the same one the model catalog draws per vendor. `identityHeaders` carries the rewrite across a whole header set, so this is the fourth caller sharing the projection rather than repeating its guards. A pair of tests pins both halves. My earlier sweep classified these two as official by their names instead of asking who chooses the URL, which is why they were missed. The contract header is also condensed here, per the convention below. * docs(agent-core-v2): condense the identity headers to their contracts The comment convention is one sentence with two halves — comments live only in the top-of-file block, *and* that block states the module's role without narrating implementation. Moving the member docs up last round satisfied the first and broke the second: the headers ended up spelling out the slug folding algorithm, the strip mechanics, and the load order. Kept what a caller or the next editor would get wrong without it (why the value is read rather than snapshotted, what `undefined` obliges a consumer to do, why this source waits for config). Dropped what the code already says. 22/12/12/13 lines, against 53 in `catalogService.ts` — length was never the problem. * fix(agent-core-v2): rebuild active prompts when the builtin skills change Reloading the catalog on a `builtin_product_skills` toggle left existing agents holding the old listing: `AgentProfileService` refreshes the prompt only for the plugin source, so a disabled switch kept advertising skills that were gone, and enabling it left them missing until an unrelated refresh. The plugin source is special because it also contributes prompt sections (#2314), and the file-backed sources are left out for cost — their fs watches would rebuild every agent's prompt on each edit. The builtin source has no watch: it changes only when its config switch is toggled, so it belongs with the plugin source rather than with the file ones. Subscribing to the catalog rather than the config section is load-bearing. The catalog fires after the contribution is replaced, whereas a config subscription would race the reload, and `resolveSkillListing` only awaits the catalog's *initial* readiness — so the rebuilt prompt could read the listing it was meant to replace. The source id is a named constant now, so the subscription does not match on a bare string. * refactor(agent-core-v2): freeze the agent identity for the process lifetime The identity is announced outward (MCP initialize, OAuth registration, provider request logs) and cannot be re-announced, so mid-process changes could only ever apply partially. Resolve it once when config first loads and hold it for the life of the process: IAgentIdentity now hands out a frozen snapshot via resolved()/current(), carrying finished products (outbound User-Agent variants, rewritten header set) so call sites stop composing host headers with the slug themselves. The kosong host-headers port carries two finished layers and the catalog only picks one; consumers gain no invalidation obligations because the value can never change after the freeze. [identity] edits take effect on the next start (documented). * fix(agent-core-v2): locate the User-Agent header case-insensitively HTTP header names are case-insensitive, but the snapshot builder looked up 'User-Agent' by exact key: an embedding host spelling it 'user-agent' got no third-party UA and kept its own product token on the services path even with an identity configured. The builder now locates every case variant and rewrites each in place, keeping the host's spelling. Also corrects the two web-service headers that still described both paths as sending the bootstrap headers, naming agentIdentity as the collaborator behind the config path, and documents that a resumed session keeps its recorded system prompt. * fix(agent-core-v2): attribute header provenance from the finished third-party layer Inspection reconstructed the non-full host layer from the raw headers with an exact-case 'User-Agent' lookup, so a host spelling the header 'user-agent' got a resolved User-Agent with no provenance entry even though the runtime sends the rewritten value. buildModel now captures the port's finished third-party layer in the trace and attribution reads it, keeping inspect() on the same resolution pass as get(). Also condenses the identity contract header to its external role, and documents that an existing MCP OAuth authorization keeps the client registration it was granted under (reset the server's auth to register under the new identity). * fix(agent-core-v2): keep web tool backends from racing the identity freeze An env-configured [services] endpoint is visible before config finishes loading, and FetchURLTool / WebSearchTool materialized their backends at construction — so a fast bootstrap could hit the identity snapshot's pre-freeze guard during agent creation, and the composed backend pinned config and login state for the agent's lifetime against the service's documented per-call resolution. Both tools now resolve their backend per invocation, the WebSearch activation gate checks presence alone through the new hasWebSearchProvider() (no provider composition, no identity read), and bind() awaits the identity freeze before materializing the model, whose resolution reads the identity through the host-headers port.	2026-08-04 22:35:15 +08:00
Haozhe	119a33f7f1	feat(minidb): persistent index generations and lifecycle hardening (#2604) ... * perf(minidb): skip idle everysec fsyncs and add lifecycle stats - everysec WAL now fsyncs on the timer only while dirty (tracked by a write/sync generation watermark); close() keeps its unconditional final sync, and background sync failures surface via walFsyncErrors plus a sticky lastWalFsyncError instead of being silently swallowed - add WAL queue/group-commit counters (walQueuedBytes, walMaxQueuedBytes, walGroupCommits, walGroupCommitFrames) and lifecycle phase stats: recovery bytes/frames/duration, index/text rebuild durations, compaction total/snapshot/rotation/postings durations, rotation pause, and query candidates/decoded/sorted rows; add a syncIntervalMs open option threaded through compaction WAL rotation - rewrite the bench on fixed-seed synthetic data with a stable machine-readable JSON report (cold open 10k/50k/100k, word/ngram search, idle-fsync acceptance, 100k compaction, event-loop delay, peak heap/RSS per scenario) and pin the schema in test/bench-json.test.ts; add app-side baselines with loose complexity budgets in sessionIndex and searchService tests - fix ClusterDb lock-pool closeAll() leaking in-flight shard opens and drain the query store's async close on server shutdown, eliminating the ENOTEMPTY directory-teardown race * perf(minidb): bound startup rebuild and steady-state hot paths - rebuild all derived indexes in one shared store walk: a single decode per record fans out to staged builders, dt rebuild reads record metadata only, and index-less opens no longer decode at all - rank full-text results with a bounded min-heap plus a stable key tie-break instead of sorting every candidate - remove/overwrite text docs via a docID -> delta-terms reverse map instead of scanning the whole delta vocabulary - validate unique batches incrementally against touched postings instead of copying the full per-index owner map - reap due TTL entries from the expiry heap on the write path instead of a full-store sweep per write * feat(session-index): add minidb read model with keyset pagination - add ISessionIndex read-model lifecycle (prepare/status, ready/degraded states) behind the persistence_minidb_readmodel experimental flag - add ISessionIndexMirror write side recording fresh summaries into a bounded, coalescing queue after the authoritative document is durable - replace the offset cursor with before/after keyset pagination; rename list/countActive to listRecent/count - extend IQueryStore with ordered columns and pageByColumn, plus getMany/listKeys/dropCollection - wire the read model through kap-server routes and start, and update the klient sessions contract - index every session for global search instead of the 500 most recent * feat(kap-server): bound search sync lifecycle, pagination, and query budgets - split search requests from sync work: searchIndex() no longer awaits runSync/reopen/reindex; a single-flight sync coordinator with debounce and backpressure runs in the background, stale generations keep serving with explicit stale/degraded state, and refresh/sync/reindex failures surface via lastRefreshError instead of being swallowed - scope file-meta keys by session id (\0meta\file\<sessionId>\<hash>) with lazy + one-shot background migration from the legacy hash-only keys, so one session sync only touches its own meta rows - make authoritative scans incremental (mtime/ino/size rescan conditions, unchanged files no longer rewrite meta) and read wire deltas in 1 MiB chunks instead of whole-file buffer + split - replace offset pagination with versioned v2 keyset page tokens (fingerprint + index generation + sort boundary); generation changes fail old tokens with invalid_page_token, legacy v1 offset tokens are served once and upgraded, and pages collect via bounded top-K instead of full sort + offset skip - add query budgets enforced at the postings/score stage: max query terms, literal length cap, postings visit budget (minidb searchBounded/maxVisits with prefix decoding that never fabricates hits and skips the postings LRU), candidate caps, deadline and text budget; truncation is reported via incomplete reasons candidate_cap/postings_budget/deadline - reopen read-only dbs by opening the next handle before closing the previous one so a failed refresh keeps the old generation serving; failed opens now self-heal through search traffic 100k-message bench: first page p95 < 300ms and page-100 cost on par with page 1; event-loop delay during queries stays sub-millisecond. * fix(minidb): poison, roll back, and recover the WAL on write failures - give WAL writes a commit point: a failed flushBatch poisons the WAL (WAL_POISONED, tracked separately as walWriteErrors vs walFsyncErrors), rejects queued frames in reverse enqueue order, and stops scheduling further batches; everysec background sync failures stay non-rejecting per stage-1 semantics - recover in place to a known-safe point: a serialized recovery chain truncates the WAL back to the first un-acked frame, rebuilds size/nextOffset, and clears the poison; writes queue behind the recovery gate (zero-cost when idle), a failed truncate flips the instance into an explicit writeDisabled state, and a stale truncate offset (WAL file replaced by a rotation) skips the truncate - roll failed flush groups back as a unit: frames are stamped with their batchId, MiniDb keeps per-group earliest pre-state, and the first rejection restores every key of the group (rejected writes no longer reappear after reopen, and in-memory state matches reopen for any failure interleaving); the per-op seq guard remains for cross-group and rotation-retry races - wrap applyOp and the following in-memory mutations so a contract violation poisons the WAL and rolls the group back instead of escaping as a half-commit; frames never enqueued (seal race) roll back per-op without poisoning - tag errors past the commit point with ambiguous: true so callers can distinguish "definitely not applied" from "maybe applied but revoked" - close() waits for the recovery chain to go idle and backup() fences behind in-flight recovery before copying files Controlled A/B bench (22 alternating iterations, 100k concurrent sets): write-path throughput regression is within the 2% budget. * fix(minidb): turn the file lock into an instance-owned serialized lease - distinguish lock ownership by instance instead of pid: every acquire mints a pid:uuid token carried by lock/bid/watch files, inspect().mine compares tokens, liveness still follows pid, tokenless legacy files keep the old stale-takeover path, and hasLiveForeignWatch excludes self by token so same-process contenders see each other (closing the double-win takeover and the cross-instance release); a live same-pid lock is still respected, and re-acquiring a held lock is idempotent - serialize acquire/renew/release through a per-instance promise-chain mutex: renew re-checks held inside the chain and release waits for an in-flight renew, eliminating the renew/rename-after-unlink ghost lock - make MiniDb.close() a state machine (open/closing/closed) with a shared closePromise: cleanup runs per-resource try/catch in dependency order (text indexes, store, valueReader, WAL, lock), aggregates every cleanup error into an AggregateError, stays in 'closing' on failure so a retry finishes the cleanup, and no longer leaks the lock when the WAL close fails; a rejected in-flight compaction no longer escapes the cleanup pass * fix(minidb): keep readers on one consistent file generation - add an internal persistent-files module as the single source of truth for the persisted file set (snapshot, WAL, sidecars, postings pattern, fingerprint subset); lock-pool fingerprints, persistentFiles, open stale-tmp cleanup, and backup/restore filtering all derive from it, and fingerprints upgrade to dev:ino:size:mtimeMs so compound sidecar changes can no longer hide from cluster readers - pair snapshot and WAL generations during recovery (transitional stat-pairing until stage-5 manifests): each pass anchors the fds it scans, re-stats afterwards, tolerates append-only WAL growth, retries bounded times on generation churn with a clean store reset, and throws RECOVERY_GENERATION_CHURN when churn exceeds the budget; the disk-mode ValueReader attach re-validates inodes so stale offsets never read a replaced file - make the rotation directory fsyncs strict: failures abort the rotation through the existing rollback path instead of being swallowed, while platforms without directory fsync degrade once with a warn and stats.dirFsyncUnsupported * fix(minidb): serialize index-definition sidecar mutations, persist before publish - extract the promise-chain mutex into a shared createSerializer() and give each sidecar family (secondary/compound/text) its own chain: create/drop run uninterruptibly (memory change + rebuild + persist), different families stay independent, and the data write path never shares these chains - reverse the publication order to staged -> persist -> publish: a create stages the definition, rebuilds via the staged builder, persists the sidecar including the new definition, then publishes atomically; any failure discards the staged state leaving live and sidecar untouched (no phantom indexes, retry-safe); a drop persists the sidecar without the definition before removing it live; text index create/drop adopt the same pattern, replacing the hand-rolled unwind, and a dropping marker keeps compaction postings rebuilds out of the persist window - feed staged indexes from the incremental write path (add/remove/ checkUnique/checkUniqueBatch visit live+staged) so writes landing in the persist window are not lost at publish; queries still see live only - harden writeFileAtomic: instance-unique tmp names (.tmp-pid-seq), a strict fsyncDir after rename so a successful persist is crash durable, and whitelist-based stale-tmp cleanup that never touches lock tmp files * fix(minidb): validate writes before any side effect, canonicalize values once - canonical value at the write boundary: the json codec re-parses the encoded bytes once and every downstream consumer (unique checks, secondary/compound/text indexes, dt extraction) sees exactly the persisted representation, so getter/toJSON/Proxy documents can no longer diverge between the index view and the storage view - reorder the set/batch pipeline so every fallible check happens before any visible side effect: prepare (key/ttl checks, encoding, canonical decode, index field extraction, tokenization) -> unique checks -> ensureMemoryFor eviction -> commit; a constraint failure now leaves the database untouched (no more evicted victims on rejected inserts), and applyOp is structurally pure against pre-validated data - tokenize at the prepare boundary: TextIndex gains prepareAdd/ addPrepared and the buildQueue carries validated key+tokens mutations instead of raw docs, so a throwing custom tokenizer can no longer poison the live view or the queue, and custom-tokenizer output is rejected per token over 0xffff bytes before it can permanently break postings rebuilds; prepared tokens are keyed by index instance so a same-name drop+create mid-write re-tokenizes instead of crossing tokenizers - strict batch structure validation: scanBatchOpRefs/decodeBatchOps reject unknown op types, out-of-bounds lengths, and trailing bytes (offset must equal body length), so a valid-CRC but malformed batch is skipped as a unit and counted via RecoveryInfo.corruptBatches instead of being partially applied Bench vs the stage-1 baseline: json write throughput regression is within the 5% budget (median ~2-4% depending on the measurement). * feat(minidb): add OpTracker drain primitive and atomic backup, harden tests - introduce the internal OpTracker (close gate + in-flight counter with enter/leave/close/whenIdle and reference-counted pause/resume) and drive every shutdown/drain path from it: WAL background syncs are tracked so close() waits out an in-flight sync before closing the fd, cluster lock-pool closeAll() closes the gates and drains busy callbacks before closing handles, and MiniDb writes pass a write gate - make backup() atomic with a defined linearization point: pause the write gate, drain in-flight writes (every acknowledged write is now included), copy to a sibling temp dir with per-file fsyncs, write the manifest last as the commit marker, and rename into place; failures clean up and leave no partial backup, and concurrent writes are rejected with BACKUP_IN_PROGRESS - reap emptied compound-index groups on remove (the groups map no longer grows monotonically), move the open-time mkdir behind the readOnly check so a read-only open of a missing directory fails with ENOENT instead of creating it, and never run a destructive rebuild for a read-only open failure (explicit or onLockFail fallback) - consolidate every review fault-injection repro into the formal suite behind deterministic barrier helpers (programmable writev/sync/ rename/tokenize hooks) and convert the six timing-based tests to barrier/tick-driven assertions; the .tmp repro scripts are removed The converted timing tests and the full suite pass 50 repeat runs (including under CPU load injection) with zero flakes. * feat(minidb): persist derived indexes as atomic generations, open from WAL delta - checkpoint the store, dt/secondary/compound indexes, and text dictionary/postings/docs into immutable generations under generations/g-NNNNNN published atomically (tmp build, per-file checksums and fsyncs, dir rename, CURRENT swap, strict dir fsyncs); the manifest records the format version, WAL/snapshot checkpoint anchors, per-index definition hashes, and codec/value-mode compatibility - open now loads the published generation and replays only the WAL delta after its checkpoint: no full value decode, corpus tokenization, or postings rewrite on a normal reopen (warm opens are 3.5-13.8x faster at 100k/1M records); a definition change rebuilds only the affected index, and corrupt generation files fall back to the previous generation or the legacy full recovery without ever touching the authoritative snapshot/WAL - build generations transactionally with compaction (rotation plus derived state publish as one unit, replacing the synchronous rebuildTextPostings tail), capture concurrent writes through a sealed op queue with byte/op caps, hard-link clean postings and the snapshot into the new generation, and repoint every live text base into the CURRENT generation after publish - cluster/read-only refresh watches CURRENT and the WAL watermark: pure generation publishes keep readers on incremental catch-up while rotations reopen onto the new generation; writers building the next generation never disturb readers of the current one - legacy databases open through the old path unchanged and gain their first generation in the background; OpenOptions.indexGenerations: false fully restores the pre-generation behavior * feat(minidb): workerize text-index builds and split MiniDb into facets - split the monolithic src/index.ts into facet modules (mini-db, types, value-codec, memory-guard, backup, query-engine, text-registry, wal-group, generation-builder/loader, write-path, read-path, index-admin, lifecycle, stats) and move text-index.ts to text-index/ - run corpus-scale text-index builds off the main thread via the bounded worker engine (src/worker/), exported through the new worker-runtime subpath, with inline fallback for small corpora and rollback switches - defer the open-time fallback text rebuild into a maintenance task; searches on a not-yet-committed base raise TextIndexBuildingError - add the unified maintenance scheduler, bounded async read surface, and a maintenance bench - kap-server search: switch to searchBoundedAsync and serve the building page while the index base rebuilds after fallback recovery - kimi-code: install the SEA-bundled minidb text-build worker at startup, bundle it via the native asset scripts, and add the startup-trace util plus the KIMI_TUI_INPUT_LATENCY debug probe * fix(minidb): treat win32 EPERM as unsupported directory fsync - extract isUnsupportedDirectoryFsyncError and cover win32 EPERM - drop the one-shot console.warn; stats.dirFsyncUnsupported carries the degraded state * fix(kap-server): harden search-index dispose and drain lifecycle - dispose() now closes an OpTracker gate and drains in-flight sync/refresh passes before closing the db, so no background write can hit a closed handle; the deleteSessionDocs loop and trailing stats write skip once the gate closes (review #20) - drainGlobalSearchDisposals loops to a fixpoint so disposals registered while a drain is in flight are also awaited (review #21) - pin the post-open failure semantics with a regression test: a failed text-index setup closes the handle and the next open reacquires the writer lock instead of self-locking read-only (review #19) - export OpTracker from the minidb root for the search service's drain * chore: fix oxlint type-aware lint errors	2026-08-04 20:38:42 +08:00
zy	3126422757	feat(mcp): carry an absolute expiresAt on the OAuth authorization-url update (#2609) ... * feat(mcp): carry an absolute expiresAt on the OAuth authorization-url update The authenticate flow waits for the OAuth callback with a fixed budget, but the authorization-url tool update surfaced to embedding hosts did not say when that window ends — hosts had to hardcode a mirror of the 15-minute constant to render countdowns. Include the absolute deadline (now + effective wait timeout) in the update payload for v1 and v2. Resolve #2607 * fix(protocol,kap-server): accept expiresAt in the OAuth authorization-url update schemas The zod validators mirrored the pre-expiresAt payload shape and would strip the new field at the kap-server boundary. --------- Co-authored-by: zouying <zouying@moonshot.cn>	2026-08-04 20:02:47 +08:00
github-actions[bot]	4ac7240fff	ci: release packages (#2469) ... Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2026-08-04 15:11:04 +08:00
Haozhe	c39687318c	fix(kap-server): accept question ids containing colons on resolve (#2585) ... * fix(kap-server): accept question ids containing colons on resolve Some OpenAI-compatible providers emit tool_call ids like `AskUserQuestion:0`, which the question service adopts as the question id. The action-suffix parse then rejected the bare resolve POST as an unsupported action (40001), so clients could never submit answers. When the suffix parse fails, fall back to matching the full tail against the pending question list before emitting 40001. Also add maxRetries to the test home cleanup to absorb the async query-store shard flush (ENOTEMPTY on macOS), matching fs.test.ts. * fix(kap-server): preserve 40902 on duplicate resolve of colon-id questions A retried bare resolve of a colon-bearing question id re-entered the invalid-suffix fallback after the question settled, found no pending match, and returned 40001 — bypassing the recently-resolved idempotency window. Accept the tail in the fallback when it is recently resolved so the shared duplicate-resolve path emits 40902 as documented.	2026-08-04 12:58:51 +08:00
Haozhe	1328b32037	feat(acp): add experimental agent-core-v2 ACP server (kimi acp-v2) (#2571) ... * feat(acp): add agent-core-v2 ACP server - add ACP session lifecycle, configuration, permissions, and event bridging - expose the experimental kimi acp-v2 command with terminal authentication - add integration coverage and workspace build configuration * test: use neutral example domains in test fixtures and docs - replace placeholder hostnames (evil.com, foo.com, internal.corp, real.corp) with example.test / example.com in agent-core-v2 and kap-server tests - replace fixture emails (x@y.com, a@x.com) with example addresses in minidb tests and README * fix(acp): align acp-server with agent-core-v2 interfaces and address review - add missing appendText to AcpHostFileSystem (IHostFileSystem drift) - replace IAgentPromptService.prompt with inject - use Turn.cancel() instead of abortController - gate FS reverse-RPCs on client capabilities, fallback to local FS - return PROTOCOL_VERSION constant instead of echoing client version - remove misleading mcpCapabilities from initialize response - dispose old session wrapper before replacing on load/resume - fix object stringification lint error in convert.ts - add acp-v2 to expected CLI sub-command list in test * fix(acp): use enqueue for prompt submission, stop advertising unimplemented builtins - replace IAgentPromptService.inject with enqueue so onBeforeSubmitPrompt hooks (prompt-blocking policy) are not bypassed - stop advertising builtin slash commands (/help, /status, etc.) until builtin command execution is implemented - add comment explaining appendText stays local (ACP has no append RPC) - update skills test to match new availableCommands behavior * fix(acp): filter turn events by turnId, surface auth failures as auth_required - track turnId in driveTurn and ignore events from unrelated turns, preventing queued prompts from settling on the running turn - reject prompt requests with auth_required when turn fails with an auth-related error code, enabling ACP client re-auth flow * fix(acp): gate acp-v2 behind experimental flag, filter sessions by cwd - add acp-v2 experimental flag (KIMI_CODE_EXPERIMENTAL_ACP_V2) and gate CLI command registration behind it - filter session/list results by requested cwd instead of returning sessions from all workspaces - detect hook-blocked prompts via PromptHandle.state and add TODO for streaming block messages once the hook context exposes them * refactor(acp-server): rewire ACP server onto the klient facade - replace direct agent-core-v2 scope/service access (ISessionLifecycleService, ISessionIndex, IEventBus, ISessionInteractionService, etc.) with the Klient facade: klient.global.sessions / klient.session(id) / agent('main') handles - drive turns via agent.prompt() + session-level agent event subscriptions instead of per-prompt IEventBus wiring; settle on turn.ended - route approval/question bridging through session.interactions events - hide the thinking config option and skill catalog behind KLIENT-GAP markers until klient exposes those surfaces - acp-fs: pass realpath through to the local inner backend - klient: session.restore() rejects both null and undefined handles * feat(agent-core-v2): add session delete and ephemeral per-session MCP servers - add ISessionLifecycleService.delete: close a live session first, then remove its persisted data, evict the index read-model entry, and append a deleted tombstone to session_index.jsonl; unknown ids raise session.not_found - add CreateSessionOptions/ResumeSessionOptions.mcpServers: session-owned MCP overlay merged over the workspace manager via MergedMcpConnectionView (an ephemeral name shadows a workspace server), never persisted, released when the session scope tears down - return PromptLaunchResult from activateSkill so callers get the launched turn id and activation failures (unknown skill, busy) surface - add ISessionSkillCatalog.list() as a wire-friendly catalog snapshot - add ISessionIndex.remove for read-model eviction on delete * feat(klient): expose session delete, per-session MCP, skills, and stream events - session lifecycle contract: delete, resume/restore options, and CreateSessionOptions.mcpServers (ephemeral per-session MCP servers) - add the session skills contract and facade accessors for the wire-friendly skill catalog snapshot - register tool.call.delta, tool.progress, and compaction.* agent stream events so consumers can subscribe with typed payloads * feat(acp-server): align ACP v2 server with acp-adapter capabilities - complete the klient-facade rewire: ACP client connection holder and the terminal/* reverse-RPC runner routed through the Agent scope - negotiate the protocol version on initialize instead of pinning v1 - compress oversized prompt images at the ACP ingestion point with a format gate, caption, and persisted originals; a cancel arriving mid-compression settles the prompt as cancelled without a turn - stream tool call args via tool.call.delta (lazy pending create, cumulative replace, started upgrade) and refresh titles via tool.progress status updates - report compaction progress and results after /compact via the compaction.* events - answer unknown slash commands locally instead of sending them to the model - accept legacy "<id>,thinking" model ids and legacy approve / approve_for_session approval option ids - keep sessions without cwd metadata in cwd-filtered session/list - sanitize wire errors: auth codes map to auth_required, turn.agent_busy to invalid_request, everything else to a fixed internal-error message - bump @agentclientprotocol/sdk to ^1.3.0 * fix(cli): drop stale registerServerCommand call and sherif ACP SDK split - commands.ts called registerServerCommand, which no longer exists on current main (the deprecated `kimi server` shim is registered via registerWebCommand), breaking typecheck, build, and every CLI test that builds the program - sherif rejects the @agentclientprotocol/sdk major split between acp-adapter (^0.23.0, production kimi acp) and acp-server (^1.3.0, experimental); the two hosts legitimately target different SDK majors, so ignore the dependency in the sherif invocation * test: update fixtures for acp-v2 flag and domain rename, refresh nix deps hash - kap-server origin.test: two CORS cases still used foo.com after the whitelist moved to foo.example.com, so the origin was no longer whitelisted and the expected CORS headers were withheld - node-sdk config.test: expect the new acp-v2 experimental flag in the harness feature metadata - flake.nix: update the fetchPnpmDeps hash for the @agentclientprotocol/sdk 1.3.0 lockfile change * fix(acp): widen the ACP v2 auth gate beyond OAuth-only providers The gate consulted only auth.summarize(), which iterates providers declaring an oauth section — configurations that authenticate with a plain apiKey or provider env-bag credentials (no OAuth at all) were rejected with auth_required even though the default model is fully usable. - klient: expose authSummaryService.ensureReady on the global auth facade (the contract already declared it) - acp-server: gate on the engine's own readiness probe for the default model — config apiKey / env-bag / OAuth token all count, matching how the model is actually used — and fall back to "any logged-in OAuth provider" (the legacy adapter's first branch) - test: an apiKey-only config passes the gate with auth enforcement on; the OAuth logout regression is unchanged * fix(acp): reject concurrent prompts instead of displacing the in-flight turn A second session/prompt while a turn is running overwrote the session's only TurnDriver: the engine quietly queues plain prompts submitted during an active turn (the launch resolves undefined, indistinguishable from a hook-blocked launch), so the first prompt never settled and both turns' events went unattributed. Guard both model-bound launch paths (plain prompt and skill activation) with a synchronous in-flight check and reject with invalid_request (turn.agent_busy), matching the legacy adapter's busy semantics. Local slash handling (builtins, unknown-command answers) is unaffected.	2026-08-04 10:20:24 +08:00
Haozhe	21185447fe	feat(agent-core-v2): add tokenCounting service with strategy config and measured anchors (#2563) ... * feat(agent-core-v2): add tokenCounting service with strategy config and measured anchors - add IAgentTokenCountingService as the single owner of token counts: context size, full-request size, and estimate primitives, replacing the scattered contextSize/tokenEstimate/fullCompaction paths - add [token_counting] config section with strategy = measured+estimated (default) / measured / estimated, plus the KIMI_TOKEN_COUNTING_STRATEGY env override; measured zeroes all estimates, estimated ignores anchors - keep a live measured-anchor ledger in TokenCountingModel: each LLM exchange writes a real anchor, undo truncates the ledger so the surviving prefix restores its REAL measured size instead of a re-estimate, and compaction rebases to a single anchor that blends the compaction exchange's measured summary output tokens - skip writing an anchor when the stream reports no usage event instead of anchoring emptyUsage() zeros, which zeroed the context size and silenced compaction for providers without usage reporting - return the strategy-resolved size (not measured) from rpc getContext so the tokenCount contract stays correct under the estimated strategy - migrate all consumers (contextMemory, fullCompaction, llmRequester, rpc, mirrorAgentRun, sessionLegacy, kap-server legacyStatus, node-sdk, kimi-inspect) to the new service; edge bridges no longer read the wire model directly - document [token_counting] and KIMI_TOKEN_COUNTING_STRATEGY in the bilingual config reference * fix(kap-server): omit maxContextTokens instead of pushing 0 when unknown - readLegacyStatus falls back to the default model's context limit when no model is bound, and omits maxContextTokens entirely when the limit is unknown (0 is the engine's UNKNOWN_CAPABILITY marker, not a real limit) - profileService no longer emits maxContextTokens in agent.status.updated when the bound model alias does not resolve * fix(agent-core-v2): resolve token_counting strategy only at the reporting edge - keep measured anchors and heuristic estimates both recorded and feeding internal logic (compaction triggers, budgets, overflow backoff) regardless of the configured strategy - add IAgentTokenCountingService.statusSize() as the single strategy-resolved outward reading and route the WS/REST/RPC status surfaces through it - fix the context-size display falling back to provider-reported usage under the estimated strategy - fix compaction overflow backoff retrying identical messages until failure under the measured strategy (the strategy-gated estimator read as 0)	2026-08-04 09:44:21 +08:00
Haozhe	6ba75a173b	feat(config): add deprecation mechanism and rename loop retry limit (#2572) ... * feat(config): add deprecation mechanism and rename loop retry limit - agent-core-v2 config: declarative section `deprecations` (deprecated TOML keys are ignored and report a warning diagnostic; the file is never rewritten) and env binding `deprecatedEnv` (old var still resolves as a fallback with a warning), surfaced via the new `IConfigService.onDidChangeDiagnostics` event - loop_control: rename `max_retries_per_step` to `max_attempts_per_step` and `KIMI_LOOP_MAX_RETRIES_PER_STEP` to `KIMI_LOOP_MAX_ATTEMPTS_PER_STEP`; `max_steps_per_run` moves onto the same mechanism (no longer silently mapped) - kap-server: push the global `event.config.warning` WS event to every connection whenever the config warning set changes - TUI: show config diagnostics in warning yellow at startup instead of the dim startup notice - docs: config-files/env-vars (en+zh), regenerated config manifest, and the agent-core-dev config guide * feat(cli): validate config.toml against v2 section registry in doctor - add v2/validate-config.ts: validate config.toml with the agent-core-v2 ConfigRegistry, reporting registered-section schema failures as errors and unknown top-level keys / deprecated keys and env vars as non-fatal warnings - route `kimi doctor` config validation through the v2 validator when the KIMI_CODE_EXPERIMENTAL_FLAG master switch is on (lazy dynamic import, keeping the v2 module graph off the default path) - let doctor checks surface non-fatal warning messages on OK results * chore: downgrade loop-control changeset to patch	2026-08-03 20:17:01 +08:00
Haozhe	071b6a50d9	refactor(kap-server): own v1 message history and snapshot assembly (#2562) ... - move the v1 message protocol and projection out of the engine into kap-server and delete the engine-side messageLegacy edge adapter - add a shared message history loader that folds the main agent's wire journal into full history across compactions, backing both the messages routes and the snapshot endpoint - drop the disk-reading SnapshotReader fast path; assemble snapshots from engine services for cold and live sessions, removing the KIMI_SNAPSHOT_READER, KIMI_SNAPSHOT_TIMEOUT_MS and KIMI_SNAPSHOT_CACHE_LIMIT knobs - collect persisted wire record rebuild helpers in the transcript service	2026-08-03 17:55:28 +08:00
Haozhe	3e425212b6	refactor(agent-core-v2): code all domain failure modes as Error2 (#2552) ... * refactor(agent-core-v2): code all domain failure modes as Error2 - wrap bare throws across agent/session/app/workspace/os/wire/kosong/mcpCore domains in coded Error2, keeping messages verbatim and moving structured data into details with the original error as cause - add new wire codes (agent.already_exists/already_running/not_a_subagent/not_owned/type_not_allowed/max_tokens_exceeded, task.limit_exceeded, cron.expression_invalid, web.invalid_url/private_address/fetch_failed, mcp.oauth_failed, skill.parse_failed/nested_too_deep, wire.migration_missing) to the protocol KimiErrorCode union and the kap-server zod schema; register shell.git_bash_not_found and session.plan_mode_invalid - re-base domain error classes onto Error2 (SkillParseError, UnsupportedSkillTypeError, HostFolder*, AgentFileParseError, NestedSkillTooDeepError, AlreadyAuthorizedError, HttpFetchError) keeping class names and instanceof consumers intact - convert caller-bug and unreachable guards outside _base to BugIndicatingError - fix the agent tool's task-limit remap never firing by branching on the task.limit_exceeded code instead of a stale message string * refactor(kosong): make ChatProviderError family born-coded via Error2 - move the provider/context code string constants to kosong/contract/errors.ts and compute each class's wire code at construction (status code / finish reason) - move sanitizeStatusErrorMessage to the contract and fold status details (statusCode / requestId / traceId) into Error2 details at birth - slim translateProviderError down to the abort guard plus the foreign-error fallback; ProtocolErrors keeps registering the domain via re-exported constants - update errors.md conventions and tests for the pass-through behavior * feat(storage): add permission_denied and disk_full error codes - extend StorageErrors with storage.permission_denied / storage.disk_full (both non-retryable, with user-facing actions) - map errno at the backend boundary in toStorageIoError: EACCES/EPERM, ENOSPC, unexpected ENOENT → not_found, everything else io_failed; the message now carries the mapped reason - register the two codes in the KimiErrorCode protocol union and the kap-server zod schema, and document the mapping in errors.md * fix(protocol): mirror all KimiErrorCode values in kimiErrorCodeSchema the zod enum lagged the type union by 35 codes (agent.*, os.fs.*, os.process.*, storage.*, wire.*, skill/task/mcp/cron/web additions), so protocol consumers could type the new codes but rejected them at runtime validation; spotted by Codex review on #2552	2026-08-03 15:31:57 +08:00