* fix(agent-core-v2): reuse the queued prompt id for a single steer
A follow-up sent during a turn minted a second context id, so cancel
while the model was still requesting could show the same text twice
and make the host prompt un-undoable. Reuse the queued prompt id when
one prompt is steered, mark that user as in-turn so undo targets the
host turn, and project it as a non-anchor origin for the client.
* fix(agent-core-v2): type in-turn steer origin on the human prompt
The human PromptOrigin type rejected the inTurn field, which failed
typecheck/build and left the generated state manifest stale.
Reserve the context message id when a prompt is steered, emit turn.steer only after that message is appended, and join live/cold transcript plus fork by the id instead of content.
* fix(agent-core-v2): avoid root watch inventory and add a kill switch
Watch concrete candidate paths so a flooded project root cannot fill the V8 heap. Allow disabling every watcher with [watch] enabled or KIMI_CODE_WATCH.
* fix(agent-core-v2): stop watching the whole .kimi-code directory
Watch missing config files on the file path itself so session writes do not reload.
* fix(agent-core-v2): keep session deletion from hanging
Deleting a live session closes it first, and three waits on that path
had no upper bound:
- AgentLifecycleService.remove() checked its 3s quiesce deadline only
after awaiting loop.settled() and the compaction promise, so a loop
that never settled after cancel() blocked agent removal, session
close and delete forever. The settle wait now races the deadline and
falls through to the existing forced-teardown path when it expires.
- HostProcess.kill() on Windows waited for taskkill to exit with no
bound. It now stops waiting after 5s.
- setSessionArchived() awaited a pending resume inside its lifecycle
critical section. A resume queued behind the archive then waited for
the archive while the archive waited for it, wedging the session's
lifecycle chain so that every later operation on the session,
delete included, never started. The resume is now settled before
the critical section is entered.
* fix(agent-core-v2): terminate a taskkill that outlives its timeout
When the 5s wait on taskkill timed out, kill() returned but the spawned
taskkill child stayed alive and referenced, so every hang leaked a
taskkill.exe process and its handle could keep the CLI or server
process from exiting. Keep the handle and, when the timeout wins, unref
it and terminate it.
* fix(agent-core-v2): never apply a compaction summary that arrives after abort
Cancelling a full compaction, or removing its agent, aborts the
compaction's signal, and the abort listener records the cancellation
and detaches the compaction right away. compactionRound() never checked
the signal again after the summary request returned, so a provider
request that finished despite the abort still went on to
applyCompaction(). That rewrote the context of a cancelled compaction,
and since agent removal now stops waiting for the compaction at its
quiesce deadline, it could also write records after the agent was torn
down and recreate files under a deleted session directory. Check the
signal after the last await and before applying the summary.
* feat(agent-core-v2): support api_key_env for provider credentials
Providers can declare api_key_env = "VAR" in config.toml to read their
Bearer token from an environment variable instead of storing it inline.
The value is resolved per request (rotation-friendly); an unset or empty
variable fails with config.invalid naming the provider and variable.
apiKey+apiKeyEnv and apiKeyEnv+oauth are rejected as conflicts.
The /models refresh path resolves the same chain (inline apiKey ->
apiKeyEnv -> env sub-table); a provider whose variable is unset lands in
failed[] without affecting others, and open-platform providers keep the
env declaration instead of persisting the resolved secret.
Custom registries: applyCustomRegistryProvider consumes the api.json env
field — imported providers get apiKeyEnv, the legacy inline apiKey is
dropped, and a hand-edited apiKeyEnv survives refreshes (tracked via
source.envKey). kimi provider add --api-key and the TUI registry token
field are now optional so public registries import without a key.
* docs: document api_key_env provider credentials
* fix(oauth): preserve hand-edited apiKeyEnv on registry refresh and address review nits
* fix(oauth): validate apiKeyEnv conflicts during refresh and address review nits
* fix(oauth): mirror apiKeyEnv in the klient provider contract and harden refresh validation
* fix(oauth): stop auto-binding registry env names to provider credentials
* fix(oauth): preserve hand-edited apiKeyEnv across registry re-imports
* fix(oauth): scope apiKeyEnv preservation to the owning registry
* fix(agent-core-v2): preserve apiKeyEnv across models.dev catalog re-imports
* fix(kap-server): drop apiKeyEnv when the provider update route receives a replacement key
* fix(agent-core-v2): replace provider credential fields on TOML writeback
* fix(kap-server): normalize whitespace-only api_key in the provider update route
* refactor(oauth): unify provider credential rules into shared primitives
A new provider-credential module in the oauth package owns the credential
precedence chain, the mutual-exclusion conflicts, the user-facing messages,
and the write-side tri-state reconciliation; the refresh orchestrator,
agent-core-v2 (model-auth, catalog, auth readiness), and the kap-server
provider routes compose it instead of re-deriving the rules per layer.
applyOpenPlatformConfig now takes credential: {apiKey}|{apiKeyEnv} and
merges onto the existing record, so open-platform refreshes no longer drop
hand-written fields (customHeaders, the env sub-table) on the inline-key
path either, and the refresh's write-then-undo block is gone.
Registry imports converge on removeCustomRegistryEntries +
applyCustomRegistryEntries (prior-snapshot provenance): the exported
capture/restore helpers are gone, the CLI persists a re-import with a
single setConfig instead of per-id removeProvider RPCs, and
default_model/default_provider survive a re-import whenever they still
resolve. kap-server's importCustomRegistry keeps the purge-then-rewrite
two-phase replace the config service's raw-merging writeback requires.
kap-server create/replace routes accept api_key_env (tri-state, mutually
exclusive with api_key), and GET /config plus the provider catalog item
expose the binding. A declared-but-unset api_key_env now fails readiness
checks with config.invalid (was auth.token_missing), matching request-time
behavior. Registry 401/403 without a key prints an authentication hint.
* fix(cli): persist registry re-import removals on both harness generations
The v2 harness's setConfig deep-merges per domain (retaining omitted keys
and skipping undefined defaults), so a shrunk re-import left removed
providers and aliases in config.toml and kept a cleared default dangling.
The CLI and TUI registry flows now share persistRegistryImport: on v2 the
removal phase and the rebuilt records go out as two atomic
replaceConfigSections writes (the writeback merges alias fields from raw
TOML, so the purge must be persisted first); on v1 the removeProvider RPC
cascades the removals before one merge write. defaultModel/defaultProvider
snapshots are captured before any removal so the restore works on both
paths.
* fix(oauth): reject oauth before the legacy env fallback and persist cleared thinking on re-import
refreshProviderModels' env sub-table fallback now throws the same
apiKey+oauth conflict the chat path rejects, instead of authenticating
with the fallback key and rewriting the provider to drop oauth.
persistRegistryImport writes the cleared thinking section through the
replacement payload, and drops the v1 fallback branch — registry imports
always persist through replaceConfigSections, so the removal phase no
longer needs per-id removeProvider RPCs.
* chore: consolidate provider credential changesets into one entry
* chore: trim changeset to the api_key_env entry
* fix: harden provider credential status and registry imports
* fix(oauth): expose browser-safe provider credential rules
* fix(node-sdk): replace serialized provider credentials
* fix(oauth): reject credential conflicts during refresh
* fix: harden custom registry re-imports
Reject reserved provider collisions and credential endpoint drift before mutation. Replace registry-owned sections atomically with compare-and-set guards, and carry the replacement contract through klient and node-sdk.
* refactor(registry): centralize custom registry import ownership
Route CLI and TUI imports through the engine via the typed SDK and Klient operation. Keep registry replacement policy inside the engine and preserve credential edits made while fetching the registry.
Cover the shared entry point with real configuration storage and memory/IPC transport tests.
* test: trim redundant api_key_env and registry-import coverage
* fix(cli): reuse the stored registry key on keyless re-import
Both first-party clients encoded "no key given" as an empty string, but
the engine's fallback chain (options.apiKey ?? registryKeyFromExisting)
only reuses the key parked in the provider's source blob when the option
is undefined. A keyless re-import of a private registry therefore went
out without an Authorization header and failed with 401 from the CLI
and the TUI dialog, while the kap-server REST route (which passes
undefined) reused the stored key fine.
Pass undefined from the CLI handler and the TUI import dialog instead
of normalizing to ''. The dialog's result type now marks apiKey
optional, matching the engine contract.
* test: pin CAS rejection and credential-conflict behavior
The coverage trim went past redundancy in three places, leaving the
PR's headline guards untested. Restore the compare-and-set rejection
path (guarded value changed on disk -> retry error, no write) and the
absent-section guard normalization in config.test.ts, the
apiKey+apiKeyEnv / apiKeyEnv+oauth conflict rejections at runtime
resolution (modelAuth) and at the refresh orchestrator (discovery,
with per-provider failure isolation), and the open-platform refresh
through api_key_env proving the resolved secret never lands in the
provider record. Also add the first direct unit tests for the shared
declaredProviderCredential / reconcileProviderCredentialUpdate
primitives.
* refactor(oauth): share reserved provider id rules between import and refresh
* Delete .changeset/registry-import-concurrent-credentials.md
Signed-off-by: 7Sageer <sag77r@hotmail.com>
* test: trim cross-layer duplicate registry and credential coverage
---------
Signed-off-by: 7Sageer <sag77r@hotmail.com>
* fix(agent-core-v2): mark MCP servers needs-auth when a tool call returns 401
* fix(agent-core-v2): cover retried MCP calls with unauthorized handling and recheck entry after close
* fix(agent-core-v2): bind MCP unauthorized reports to the originating client
* fix(agent-core-v2): invalidate rejected MCP OAuth tokens when entering needs-auth
* fix(agent-core-v2): preserve concurrent MCP OAuth grants and recheck entry after credential awaits
* fix(agent-core-v2): flip MCP servers to needs-auth before invalidating rejected tokens
* fix(agent-core-v2): compare-and-clear rejected MCP OAuth tokens and tolerate cleanup failures
* refactor(agent-core-v2): move rejected-grant handling into the MCP OAuth service
* fix(agent-core-v2): compare MCP OAuth grant age with the scheduler clock
* fix(agent-core-v2): reject future timestamps from the concurrent MCP grant window
* fix(agent-core-v2): distinguish concurrent MCP grants from freshly rejected ones
* fix(agent-core-v2): ignore application-level MCP errors in the unauthorized sniff
* test(agent-core-v2): trim MCP unauthorized tests to the core contract
* Delete .changeset/mcp-oauth-clear-if-current.md
Signed-off-by: 7Sageer <sag77r@hotmail.com>
---------
Signed-off-by: 7Sageer <sag77r@hotmail.com>
* feat(agent-core-v2): add skill scopes and mark custom-theme as tui-only
Builtin skills can now declare a scopes whitelist (tui | web); skills
without scopes stay visible everywhere. The value is carried through
SkillSummary, the klient RPC contract, and the kap-server REST wire,
and the TUI slash commands filter by it. HTTP clients (code-app) drop
skills whose scopes exclude their own UI mode, so TUI-only skills like
/custom-theme no longer leak into app/web.
* fix: filter scoped skills from the acp and vscode palettes
ACP slash commands and the VS Code GetSlashCommands handler also
project SkillSummary lists; both now drop skills that carry a scopes
restriction so tui-scoped skills stay out of non-tui clients.
* fix(agent-core-v2): watch Windows 8.3 short paths through their long form
Watching a directory given in 8.3 short form (for example
C:\Users\RUNNER~1\...) makes libuv's Windows file watcher abort the process
with "Assertion failed: !_wcsnicmp(filename, dir, dirlen)" in fs-event.c,
because change notifications arrive under the long path.
On Windows, resolve a watch root containing a short-name segment to its long
form (the nearest existing ancestor when the root does not exist yet) and map
reported changes and ignore checks back to the requested path, so callers that
compare change paths with their own keep working.
* test(agent-core-v2): keep watch tests portable to Windows runners
* test(agent-core-v2): show received events when the Windows short path watch test fails
* test(agent-core-v2): derive the Windows short path without cmd quoting
* chore: add changeset for the Windows short path watch fix
* fix(agent-core-v2): keep watch children whose names start with two dots inside the root
relative() returns "..cache/x" for a child named "..cache", which the
startsWith('..') check treated as a path outside the watched root. Mapped
change paths then kept the resolved long form, and native signal events for
such children skipped the ignore predicate. Only a bare ".." segment, ".."
followed by a separator, or an absolute result is outside the root.
Store the optional metadata object on prompt submission and skill activation as opaque client metadata on the user or skill-activation origin, carry it through prompt events, the transcript projector, snapshots and history rebuilds, and echo it on prompt items without adding it to model content. Use display_text entries for session titles, undo labels and fork titles when every entry provides one. Project user turn payloads, live and rebuilt, through a path-free projection.
Accept skill_activation origins with a user-slash trigger in onTurnSteered so a slash command sent while a turn is running gets a transcript frame, and keep those frames from draining a queued prompt's id. Project origin file attachments onto steered frames on both the immediate and deferred paths, matching onTurnStarted and the history rebuild.
Widen activateSkillAttachmentSchema so the attachments array accepts text parts alongside image, video and file, letting a caller interleave text and media in the order the model should read them. Schema only; the route already resolves attachments as WireContent.
Media name preservation already ships: the REST schemas expose a name on
image and video content, and kap-server reads imageUrl.name and videoUrl.name
when projecting messages and prompt content. The kosong part types never
declared the field, so it survived only because object literals keep excess
properties through an assignment. Consumers that read these types directly
cannot see the name at all.
Declare it where the other optional part fields live. No runtime change; the
existing media name projection tests continue to cover the behavior.
* feat(agent-core-v2): upload images as file references for Kimi models
* fix(agent-core-v2): scope media upload cache by endpoint and recognize SDK auth error status
* fix(agent-core-v2): restore the stripped /v1 for kimi files uploads on the anthropic route
* feat(agent-core-v2): omit oldest media when accumulated inline media exceed the request budget
* fix(agent-core-v2): key the media upload cache by the stable JWT subject
* fix(agent-core-v2): harden media request recovery
* fix(agent-core-v2): correct image memo accounting
* feat(agent-core-v2): include saved paths in dropped media placeholders
* docs: drop the saved-path re-read guarantee from the media budget note
The guarantee does not hold for inline data-URL media (no persisted
path exists), and the runtime warning already conveys path availability
when it applies. Addresses the codex P2 review suggestion by removal.
* perf(tui): batch and cache agent swarm progress rendering
* perf(agent-core-v2): evict completed subagent scopes behind an LRU cache
* fix(agent-core-v2): stop the agent actor in the session machine when its scope is removed
* fix(agent-core-v2): emit a terminal event for the final rate-limited run and defer eviction while background tasks run
* fix(agent-core-v2): include in-flight retries when abandoning suspended agents
* fix(agent-core-v2): roll back the closing flag when scope removal fails and wait per the configured eviction timeout
* fix(agent-core-v2): terminalize subagents spawned after batch cancellation and report task timeouts as failures
* chore: restore upstream/main state of files mangled by lint-staged autofix in the merge commit
oxlint --fix rewrites (prefer-set-has, catch-error-name, prefer toSorted/.at(-1)/toReversed)
touched seven files the branch never modified; one of them (oauth managed-kimi-code.ts)
no longer typechecks. Restore all seven to their exact upstream/main state. Committed
with --no-verify so the same autofix does not re-mangle them.
* fix(agent-core-v2): retry deferred scope evictions without exhausting the attempt budget, dedupe terminal events for starting retries, and patch-level the changeset
* fix(agent-core-v2): finish scope teardown instead of reactivating a partially torn-down scope
* fix(agent-core-v2): terminalize subagent-start hook cancellations and re-acquire resume targets after metadata reads
* fix(tui): record cancelled background agents in the transcript
* fix(agent-core-v2): route mirror terminal events through the batch exactly-once guard
* fix(tui): guard terminal swarm members from re-cancellation and deliver terminal status to cancelled foreground subagent cards
* fix(agent-core-v2): classify eviction as removed when teardown already closed the scope
* Merge remote-tracking branch 'upstream/main' into perf/subagent-scope-eviction
Skip lint-staged for this merge: its oxlint --fix pass rewrites unrelated files
(prefer-set-has etc. mangled seven files in the previous merge commit), while the
merge content is upstream's lint-clean code plus conflict resolutions already
verified by oxlint.
* chore: restore upstream/main changes dropped by a stash roundtrip during the merge
A git stash/pop cycle used to isolate an unrelated flaky test reverted 82 files of the
merge result to the pre-merge branch state, so commit 375ff2a4a missed them. The
working tree already held the correct merged content; this commit restores it.
* fix(agent-core-v2): propagate the cancellation reason from turn abort to tool signals
Cancelling a turn aborted the turn's llm scope and every tool scope
without a reason, so tools and subagents only ever saw the default
AbortError and could not tell a user cancellation from a system abort.
With the swarm terminal-event classification this surfaced as
`subagent.failed` ("This operation was aborted") on Ctrl+C instead of
`subagent.cancelled`.
Carry the reason end to end: `MachineEngine.abort(reason)` sends it on
`input.abort`, the agent machine remembers it for the turn and forwards
it to `turn.abort` and to every tool scope it aborts, the turn machine
passes it to the llm scope, and the loop service hands its cancellation
(a `UserCancellationError` by default) to the engine.
* fix(agent-core-v2): stop rebuilding an evicted subagent after its caller aborts
`createAgentAwaitingClose` polled for the previous scope to finish
closing without ever looking at the caller's abort signal, so cancelling
an `Agent` or `AgentSwarm` resume during that wait still recreated the
scope afterwards. In the `Agent` path the run then rejected before any
terminal event was mirrored, leaving an idle scope that the scope cache
no longer tracked.
Thread the caller's signal into the helper and check it before every
attempt; the Agent tool passes its call controller and the swarm service
passes the attempt signal. Also trim the eviction changeset to the one
sentence the changeset rules ask for.
* fix(agent-core-v2): report task-manager aborts of a subagent as cancelled
When the task manager times out or stops a background subagent it aborts
the run with a plain reason ('Timed out', the TaskStop reason), and the
run rejects with that raw reason. The task manager therefore classifies
the task as timed_out or killed, but the mirror only recognised
`UserCancellationError` as a cancellation and emitted `subagent.failed`,
so the transcript recorded a failure before the authoritative
`background.task.terminated` event could land.
Classify a terminated run by the shape of its abort reason: a real
Error that is not an AbortError (the swarm's own per-item timeout) stays
a failure, everything else that aborted the run is a cancellation. The
swarm's start-failure path uses the same rule.
* fix(agent-core-v2): flush the wire before evicting a subagent scope and re-pick LRU candidates
Two gaps in the scope-cache eviction pass:
- `AgentLifecycleService.remove()` swallows a failed wire flush and still
tears the scope down, so an eviction that hit a disk-full or transient
I/O error would drop the in-memory scope and let a later resume rebuild
from a stale wire. Flush the agent's wire explicitly before removing;
if that fails, keep the scope resident and retry on a later pass. The
idle and task checks are repeated after the flush so a resume that
started meanwhile is not cancelled by the removal.
- The pass snapshotted its candidates up front and re-validated them by
attempt count only, so a scope that was resumed and completed again
while an earlier eviction was awaited kept matching with attempts 0 and
was evicted despite now being the most recently used. Pick the oldest
eligible entry from the live map on every step instead, skipping only
the entries this pass already tried.
---------
Co-authored-by: Kaiyi <me@kaiyi.cool>
* fix(plugins): rename WebBridge display name to Kimi Browser Extension
The product has renamed WebBridge to Kimi Browser Extension in work and
Chrome. Update the user-facing display name across the built-in
capability entry, TUI plugins selector, managed plugin manifest,
marketplace catalog, skill docs, and user docs to match. Internal ids,
binary names, CDN paths, and daemon references are unchanged.
* fix(plugins): bump webbridge to 1.11.4 and keep legacy docs anchor
Address review: point the changeset at the scoped CLI package, bump the
renamed plugin's manifest/catalog/docs version so installed users are
offered the renamed package as an update, and preserve the published
#kimi-webbridge documentation anchor beside the renamed heading.
* docs(plugins): match only the known extension-update error messages
Broadening the version-mismatch trigger to the generic prefix 'Please
update the' would misclassify unrelated tool errors as an outdated
browser extension; match the two known full messages instead.
---------
Co-authored-by: kimi-agent-bot <kimi-agent-bot@users.noreply.github.com>
The platform /usages payload now serves per-window used ratios
(goods_version, a usages map of limit5h/limit7d/monthTotal/monthCode
entries with used_ratio/reset_time, and boosterWallet) instead of
absolute used/limit rows.
- oauth: parse and fetch the quota model; keep the platform helpers
- toolkit / agent-core-v2 / node-sdk: getManagedUsage returns the quota
- kap-server: /oauth/usage passes the camelCase quota shape through
(the legacy snake_case wire is gone)
- TUI /usage: plan rows are presence-driven from the quota payload;
the monthly row carries a kimi/code breakdown line
- docs: server-api reference updated for the new response shape
* feat(agent-core-v2): fail fast on unsupported [secondary_model].default_effort
* fix(agent-core-v2): reject default_effort off for always-thinking pool models
* fix(agent-core-v2): surface adaptive_thinking on the assembled catalog model
* perf(agent-core-v2): shard the session event bus by agent id
* fix(agent-core-v2): preserve full-stream-before-typed ordering in agent channels and render perAgent counts in the inspector
* fix(agent-core-v2): deliver agent full streams before session typed handlers and dispose sharded channels with the bus
* fix(agent-core-v2): prevent rebuilding agent channels after the event bus is disposed
* fix(agent-core-v2): isolate agent channels on generation replace and keep typed handlers on the shared per-type channel
* fix(agent-core-v2): require the active lifecycle context before firing an agent full-stream channel
* fix(agent-core-v2): reject stale lifecycle contexts when subscribing to an agent full-stream channel
* fix(agent-core-v2): honor the agent context in typed subscribeAgent subscriptions
* fix(agent-core-v2): release disposed agent scopes from the DI dependency graph
* fix(agent-core-v2): drop retired service instances from the tracked edge nodes and the dependency graph
* fix(agent-core-v2): resolve tower roster identities to the latest registration
Agent ids restart from agent-0 in each session, so a freshly spawned
worker collided with the previous session's roster entry and every
find-first lookup (caller identity, write guard, death bookkeeping)
resolved to the stale entry: workers read the wrong inbox, sent under
the wrong name, and were denied their own writes, mission updates, and
reviews.
- resolveAgent picks the latest roster entry for an agent id; all
callers (resolveCallerName, write guard, resume veto, died/revived)
go through it
- registerAgent retires same-agent-id entries before appending
- enter() (/tower on) now adopts the workspace roster itself instead of
relying on a manual TowerInit
* fix(agent-core-v2): adopt the tower roster when a replayed tower mode finds a dead foreign owner
A forked or restored session replays the durable TowerModeEnter into an
active tower mode without ever calling enter(), so the roster adoption
added there never ran on the restore path: with the previous owner
session gone, the fork kept the mode (and the stale roster) until a
manual TowerInit. The dead-owner branch of the restore-time
reconciliation now adopts the workspace, mirroring enter()'s takeover
of an idle owner; a live foreign owner still causes an exit.
* fix(agent-core-v2): await the outgoing tower owner's release before adopting its roster
Taking tower mode over from a live but idle owner called the owner's
synchronous exit(), whose ownership release ran fire-and-forget, and
immediately adopted the roster — two concurrent load-modify-save cycles
on .tower/comms/state.json that could lose the new owner or resurrect
the stale roster. exit() now awaits the ownership release and the
takeover awaits the owner's exit(); the remaining callers either await
(RPC/HTTP tower-mode-off) or explicitly ignore the promise (mode mutex,
restore-time self-exit).
* fix(agent-core-v2): fail tower activation when the roster adoption cannot complete
Adoption failures (unreadable or unpersistable state.json) were
swallowed into a log warning, so enter() and the stale-owner restore
both activated tower mode with the foreign owner and stale roster still
in place — the exact identity mismatch the adoption is meant to
prevent, now with a false success report. adoptTowerRoster() now throws
a TowerProtocolError with the underlying cause: enter() propagates it
before any tool is activated, and the restore path drops the replayed
tower mode instead (it must not throw inside the restore hook chain).
* fix(agent-core-v2): propagate unreadable tower state during roster adoption
adopt() treated any state.json read failure as an uninitialized
workspace via isInitialized()'s catch-all, so an existing but
unreadable state file (EACCES, EISDIR, transient I/O) reported a
successful no-op adoption and enter() activated tower mode against the
foreign state — bypassing the activation guard added in the previous
commit. Only ENOENT now means uninitialized; every other read error
propagates into the fail-activation / deactivate-on-restore paths.
---------
Co-authored-by: konghuanjun <konghuanjun@moonshot.ai>
* feat(oauth): add the dynamically_loaded_tools capability from the official models endpoint
* feat(agent-core-v2): support per-server deferred disclosure of MCP tools
* feat(klient): mirror per-server deferred in the MCP config contract
* fix(agent-core-v2): honor per-server deferred for the needs-auth MCP tool
* fix(agent-core-v2): register select_tools regardless of the profile tool allowlist
* feat(agent-core-v2): default MCP servers to inline tool disclosure unless deferred is enabled
* refactor(agent-core-v2): fold the prompt queue into the agent loop service
Delete AgentPromptService/IAgentPromptService: prompt submit/queue/steer/
abort now ride the agent machine queue through IAgentLoopService's extended
surface (submitPrompt/submitSteerPrompt/enqueuePrompt/steerPrompts/
abortPrompt/drainPrompts/injectPrompt/retryPrompt/promptQueue plus
hooks.onBeforeSubmitPrompt and the promptAdmission reservation slot).
Durable prompt.* event classes move to agent/prompt/promptEvents.ts and keep
their registrations; promptAdmissionKey keeps its fold. Dead assets go away:
promptResolutionKey, PROMPT_ALREADY_COMPLETED (kap-server 40903 path),
promptLaunchingKey and clear(). Compaction gating (queue while compacting,
resume on finish) moves into the loop reservation drain.
The 'agentPromptService' wire name keeps its shape: a thin AgentPromptChannel
facade (same decorator id) forwards submit/submitSteer to the loop, so
klient memory/ipc/debug transports and the kap-server dispatcher are
unchanged.
* test(agent-core-v2): re-pin prompt queue semantics on the loop service
Rewrite promptService.test.ts (25 cases, count unchanged) against the real
AgentLoopService with the scripted-LLM harness, fold the launch-window
reservation out of promptQueue().pending to match the old snapshot contract
exactly, and update the debug-channels pin to the facade's submit/submitSteer
surface.
* refactor(agent-core-v2): lint-align the loop prompt queue surface
* fix(agent-core-v2): settle prompt completions on the turn-result chain
Match the deleted service's microtask position: prompt.completed/aborted and
the completion deferreds fire from a result.then chain attached at bind time
instead of synchronously inside endTurn, so wire/emit ordering with
post-turn producers (tool unregister, next-prompt launch) stays identical to
the baseline snapshots. Steered children move onto the reservation so the
chain can settle them after the active turn is gone.
* refactor(agent-core-v2): move the prompt-submit gate into the agent machine
* refactor(agent-core-v2): keep image compression captions inline in prompt messages
* refactor(agent-core-v2): drop the durable prompt admission facility
* refactor(kap-server): resolve prompt auth at turn runtime instead of submit time
* refactor(agent-core-v2): teach the agent machine queue metadata, multi-id steer, gate rewrite, and pause
* refactor(agent-core-v2): converge prompt submission on machine queue user entries
* refactor(agent-core-v2): replace loop prompt records with a waiter registry fed by machine events
* feat(agent-core-v2): make the compaction attempt limit configurable
Add loop_control.compaction_max_attempts (default 5) to control the
maximum total attempts for a failing compaction request, replacing the
hardcoded MAX_COMPACTION_RETRY_ATTEMPTS constant. The value flows
through ProfileModelContext into the compaction retry loop, covering
both retryable generation errors and empty/truncated response shrinks.
* fix(agent-core-v2): bound compaction shrink attempts and compute retry delays lazily
Address codex review on #3750: the empty/truncated shrink path allowed
maxAttempts + 1 requests (throwing only when the shrink counter exceeded
the limit), and the backoff delay array was allocated eagerly with
maxAttempts - 1 entries before the first request. The shrink path now
stops at the configured limit, and each delay is computed lazily from
the retry index.
* fix(agent-core-v2): count every compaction request against the shared attempt limit
Address the second codex review round on #3750: the retryable-error and
empty/truncated recovery paths kept separate counters, and the retry
budget reset after each shrink, so alternating failure modes could issue
more requests than compaction_max_attempts. A single requestAttempts
counter now gates all recovery paths (the overflow shrink path keeps its
own tighter cap of 3), making the configured value a true maximum on
total requests per compaction round.
