Core

The core subsystem is packages/core — the packages every composition boots: the event-sourced session log, system-prompt assembly, the tool registry, the agent types, and the concrete loop that drives them. This page explains what the agent/agent-loop pair declares — how an agent is created and owned, and the Agent handle's delivery, cancellation, and interception contracts — plus the two type patterns every subsystem follows. The group's dedicated pages and the rest of the folder are indexed in the subsystems README.

The spine, package by package

A turn flows through the six packages in one loop: the driver in agent-loop claims a queued prompt, opens a turn on the session log (ctx.sessions), assembles the request prefix through system-prompt (ctx.systemPrompt) and derives history from the log, streams the model response through the LLM seam, dispatches tool calls through the tool registry (ctx.tools), and appends every model-visible fact back onto the log before the next step derives from it. The conversation vocabulary the loop moves — Message, ContentBlock, StreamChunk, the model request — is declared by packages/llm and documented on llm-streaming.md.

Package	Owns	Page
session/	The append-only SessionEvent log and in-memory store — the single source of truth (ctx.sessions)	session.md
system-prompt/	Prompt-section and tool-schema assembly (ctx.systemPrompt)	system-prompt.md
tools/	The scoped tool registry and guarded execution pipeline (ctx.tools)	tools.md
agent/	The Agent interface, live registry, initiator scope, and agent/* event vocabulary (ctx.agents)	this page
agent-loop/	The concrete driver implementing the public Agent contract (ctx.agentLoop)	this page
scope/	The scoped-registration primitive the registries and loop build per-agent scoping on	scope.md

scope/ is the one non-service package: a dependency-free library (createScope/scopeOf/scopeTarget) that sits below session/ and system-prompt/ in the module graph precisely so they can consume it without a cycle. agent-loop is the one concrete implementation of the public Agent contract and lives here because it is the harness's default product loop; it runs each driver inside ctx.agents.withInitiator(). Extension plugins depend on agent — including when they need the initiating Agent — and never on agent-loop directly, so the loop stays swappable. The default composition that wires this spine into a runnable agent is examples/agent-spine-demo.

Creation and ownership

Consumers create agents through ctx.agents — create() builds a fresh session and agent under one caller-supplied SessionId, resume() loads a persisted session first — or declaratively through the loop's config entries. Programmatic creation returns the owner's handle:

Source: packages/core/agent/src/index.ts

/**
 * An owned agent plus its disposer, returned by {@link AgentRegistry.create} /
 * {@link AgentRegistry.resume}. The disposer is a CAPABILITY: among consumers,
 * only the holder can tear this agent down. The registered factory provider is
 * also a structural owner because the scoped agent depends on that provider's
 * service API; provider unload stops and drains every live handle it made.
 * `dispose()` stops the loop, awaits its exit, unregisters the agent, removes
 * its session from the store, and finally unwinds its scoped world.
 *
 * `ctx.agents.get(id)` still returns a bare {@link Agent} — the handle is
 * exposed only to the consumer owner that created it; the structural provider
 * reaches the same teardown internally. Config-created agents (the loop's own
 * startup) are owned by the loop fiber and never need a handle.
 */
interface AgentHandle {
  agent: Agent
  dispose(): Promise<void>
}

CreateAgentOptions carries the shared identity and everything a fresh agent needs before publication: session metadata (meta — validated cwd, fork lineage, seed boundary, origin classification, delegation depth), an optional seed replay prefix for forks, per-agent AgentOptions, a creation-only cancellation signal, and setup. ResumeAgentOptions is the persisted-identity counterpart: resumeSessionId, agentOptions, signal, and setup. The setup callback (AgentSetup) composes the agent's scoped world while both ids are still unpublished — everything registered through agentCtx exists before agent/created and the first prompt assembly — and may return a synchronous commit invoked immediately before publication; a setup rejection, commit throw, or owner disposal rolls the transaction back without publishing either id.

AgentFactory is the creation interface behind the registry: the loop registers its factory via ctx.agents.setFactory(), so consumers use ctx.agents without depending on the concrete loop package. The exact create/resume signatures and rollback contracts are in the generated section below.

The agent handle

Agent is the surface every plugin (UI, hooks, orchestrators) programs against; ctx.agents.get(id) returns it, and the initiator scope carries it. The concrete implementation is package-internal to dsh-agent-loop; nothing outside the loop depends on it. The unified send method exposes target and wakeup routing directly; followup, steer, and inject are fixed-preset aliases.

Source: packages/core/agent/src/types.ts

/** Public live-agent handle. */
interface Agent {
  /** The single identity shared with {@link session}. */
  readonly id: SessionId
  /** The provider route and model this agent's requests use. */
  readonly options: AgentOptions
  /** The live session this agent drives; its log is the durable source of truth. */
  readonly session: Session
  /** The agent-owned projection of durable pending work. */
  readonly inbox: Inbox
  /** The current lifecycle state, mirrored on every `agent/status` transition. */
  readonly status: AgentStatus
  /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */
  readonly ctx: Context

  /**
   * Clear queued and steering work — unless `keepInbox` — and abort the active
   * turn or between-turn task. The first cause wins for that activity. With no
   * active activity, cancellation is a no-op and does not arm later work.
   * @param cause - the stable caller intent carried by the active operation signal.
   * @param options - cancellation options; `keepInbox` preserves pending work.
   */
  cancel(cause: AgentCancelCause, options?: CancelOptions): void

  /**
   * Resolve after the current whole-agent activity reaches quiescence. This
   * follows replacement work started before the observed driver retires,
   * but does not identify the settlement of any particular message.
   * @returns fulfillment after no active driver or maintenance task remains.
   */
  whenIdle(): Promise<void>

  /**
   * Run one non-turn maintenance task from the true idle phase. The task starts
   * synchronously after claiming that phase; later waking input remains in the
   * inbox until the task settles, while public status stays `idle`.
   * `whenIdle()` follows both the task and any waking work released behind it.
   * @param task - operation whose fulfillment or rejection is preserved, with a signal aborted by {@link cancel}.
   * @throws synchronously when turn-driving or another maintenance task already owns the agent.
   * @returns the task promise.
   */
  runMaintenance<T>(task: (signal: AbortSignal) => Promise<T>): Promise<T>

  /**
   * Route identified input to an inbox boundary and optionally wake the driver.
   * Waking input submitted after active cancellation is queued for the next
   * turn and runs when the aborted activity converges to idle; a `disposed`
   * cancel leaves it parked. A wake submitted while already idle always opens
   * its turn boundary, even when its message is cleared before the driver
   * claims ([cancel-convergence wake latch](../../../../.agents/notes/implemented/bug-fix/2026-08-07-cancel-convergence-wake-latch.md)).
   * @param message - identified content and the source that supplied it.
   * @param target - the preferred next-turn or next-step inbox boundary.
   * @param wakeup - whether delivery may wake the driver.
   */
  send(message: UserMessage, target: InboxTarget, wakeup: boolean): void

  /**
   * Queue an ordinary follow-up turn and wake the driver. The item becomes the
   * sole ordinary message of its own turn.
   * @param message - identified prompt content and the source that supplied it.
   */
  followup(message: UserMessage): void

  /**
   * Submit steering for the nearest step. An idle driver starts a turn;
   * a running driver consumes it at its next step boundary.
   * A rejected step leaves steering parked in the inbox until the next
   * wake; cancellation or disposal may discard pending steering.
   * @param message - identified steering content and the source that supplied it.
   */
  steer(message: UserMessage): void

  /**
   * Queue model-facing context for the next pre-step without waking the
   * driver. A running driver claims it at the nearest later step boundary;
   * idle drivers leave it pending until follow-up or steering
   * wakes them. It may miss a request whose pre-step already claimed its
   * batch. Cancellation or disposal may discard pending context.
   * @param message - identified injected context and the source that supplied it.
   */
  inject(message: UserMessage): void
}

/**
 * An agent's lifecycle state, emitted on every transition as `agent/status`:
 * `idle` means no driver is active; `running` begins when waking input starts
 * cancellable pre-step processing and lasts while the driver drains,
 * closes, or checkpoints turns. Disposal removes the agent from its registry;
 * it is not a third observable status.
 */
type AgentStatus = 'idle' | 'running'

running describes the driver-wide drain interval and may span consecutive queued turns; it does not prove a turn is still open. Disposal removes the agent from the registry and emits agent/disposed; it is not a terminal status value. followup() returns no handle: its MessageId identifies durable inbox insertion, claim, and discard facts, not a later assistant output or turn ending. whenIdle() observes the whole agent, so callers may call a receipt-to-idle interval a run only when they explicitly own that interval (decision).

/** Merge-extensible agent creation options. Persona belongs to system-prompt sections. */
interface AgentOptions {
  /** Provider route (must have a registered adapter at call time). */
  provider?: string
  /** Model id interpreted by the selected provider adapter. */
  model?: string
  /** Maximum output tokens for each conversation-model request. */
  maxTokens?: number
}

Dispatch requires provider and model after agent/request. When present, maxTokens must be a positive safe integer and caps every conversation-model request; omission allows the exact-model adapter default to materialize before the request header, or otherwise leaves provider behavior unchanged. An agent-scoped deployment:persona prompt section may shadow the global default persona.

The inbox is the delivery vocabulary — two ordered pending-message lists the agent owns as a durable projection:

/** One of the two ordered pending-message lists owned by an agent. */
type InboxTarget = 'next-turn' | 'next-step'

Every pending occurrence is its UserMessage; MessageId is the sole identity. Inbox.append, prepend, replace, remove, clear, splice, and claim record normalized durable agent/inbox/spliced mutations and reject duplicate pending ids. replace(messageId, newMessage) and remove(messageId) locate the pending message across both lists; replacement may change identity and emits the old message as discarded followed by the new message as inserted. Ordinary removals and clear() are cancellations. claim(target) removes the proposed step batch — all next-step input plus, at a turn boundary, one next-turn message — through pure deletion splices without emitting discarded notifications, and the loop separately emits per-message claimed notifications. Whole-queue consumers such as UI projections reconstruct nextTurn and nextStep from the durable splices, while consumers following one message use the exact agent/inbox/inserted, claimed, and discarded notifications.

Cancellation:

/** Options for {@link Agent.cancel}. */
interface CancelOptions {
  /**
   * Preserve queued and steering inbox items instead of discarding them. The
   * active turn is still aborted, but un-started and pending work survives for a
   * later turn and no canceled inbox splice is logged.
   */
  keepInbox?: boolean | undefined
}

/** Why an active agent driver was cancelled. */
type AgentCancelCause =
  | { readonly kind: 'user' }
  | { readonly kind: 'parent' }
  | { readonly kind: 'hook'; readonly reason: string }
  | { readonly kind: 'disposed' }

The cause is a TypeScript-enforced same-process input. An active cancellation holder copies it into the runtime-only AbortSignal.reason; a signal grants cooperating listeners no classification authority. Durable turn/end retains the coarse { kind: 'aborted' } outcome; recording who requested cancellation would require a separate durable event rather than overloading the terminal result.

The event taxonomy owns the agent/* lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits.

Initiating Agent

The process-local initiator carried by ctx.agents is the exact Agent above, not a separate frame or copied identity. Ambient presence is neither liveness proof nor authorization; the initiator-scope decision defines its lifetime and scope rules.

Interception decisions

Pre-step decisions use the same identified UserMessage type as durable user-role input. The entered batch is authoritative and preserves every message's id and source. Hook bridges map their native decision fields onto this typed result.

Source: packages/core/agent/src/types.ts

agent/pre-step receives one payload carrying the exclusive claimed batch (messages), the proposed step's coordinates (turn, step), and the current turn's cancellation signal. The initial proposal runs inside an open turn before any step; a tool continuation may submit an empty claimed batch between steps:

It returns a PreStepDecision. Reject opens no step. Enter supplies the complete message batch appended after step/start; claimed messages omitted by the final decision remain removed, while input inserted after the claim stays pending:

/** Whether and with which messages the loop enters a proposed step. */
type PreStepDecision =
  | { kind: 'reject' }
  | { kind: 'enter'; messages: UserMessage[] }

agent/request-error runs after a failed model step closes and before its turn closes. Listeners can repair durable state or await policy work while the failed turn's signal is still live. A handling listener returns { kind: 'retry' } without calling next(); the default undefined leaves the failure terminal.

/** Action returned by a listener that owns model-request recovery. */
type RequestErrorAction = { kind: 'retry' } | undefined

agent/pre-step is the only serial listener chain before request derivation. agent/turn-stopping runs when a turn has no tool or steering continuation, before one final steering drain.

agent/session-start carries a SessionStartSource (why the session lifecycle began; a bridge keys its SessionStart matcher on it):

/** Why a session lifecycle began; seeded creates are `startup`, while persisted loads are `resume`. */
type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact'

Sessions

A Session is an append-only log of typed SessionEvents — the single source of truth. The LLM message history is derived from the log (deriveMessages()), not stored separately. Every entry carries a monotonic seq, a time, and a type-discriminated data payload; surface variants may also list cited earlier events in sourceEventSeqs and carry a surfaceOp.

The SessionEvent envelope's exact conditional fields, the twelve event variants (turn/start, turn/end, step/start, step/end, user/message, assistant/chunk, assistant/message, tool/call, tool/result, steering/message, todo/write, request/header), the deriveMessages() projection rules, the TurnTrigger/TurnEndReason reasons, and the execution-enclosure and standalone-event rules are on session.md. How the log is made durable — the SessionPersistence interface, JSONL/SQLite backends, the session/flush checkpoint, crash recovery, and SessionHeader — is on persistence.md.

ToolDefinition

The one pipeline-authoring type that is core: what every registered tool is — a model-facing ToolSchema plus an execute function and optional final-content and UI callbacks. A tool author rarely constructs it by hand (the defineTool DSL builds it with typed arguments), but it is the contract the registry holds and the loop dispatches through.

Its full fields, the defineTool/ValueSchemaSpec/ParameterSchemaSpec typed schema DSL, the ToolExecution/ToolExecutionResult waterfall types, and the tool-presentation UI types are on tools.md.

Repo-wide type patterns

Two patterns recur across every subsystem and are documented once, here.

The …Map → derived-union pattern

Almost every extensible sum type in the harness follows one pattern: an interface keyed by a discriminant tag (the …Map), from which the union is derived with keyof. Plugins add variants by declaration merging — no edit to the owning package.

// The pattern, schematically:
interface ThingMap {
  'a': { kind: 'a'; /* … */ }
  'b': { kind: 'b'; /* … */ }
}
type ThingKind = keyof ThingMap          // 'a' | 'b'
type Thing = ThingMap[keyof ThingMap]    // the discriminated union

// A plugin extends it without touching the source package:
declare module '@deepseek-ai/dsh-llm' {
  interface ThingMap {
    'c': { kind: 'c'; /* … */ }
  }
}

Six canonical maps use this pattern; a plugin author extends these:

Map	Package	Derives	Catalog
ContentBlockMap	dsh-llm	ContentBlock	llm-streaming.md
MessageSourceMap	dsh-llm	MessageSource	llm-streaming.md
FinishReasonMap	dsh-llm	FinishReason	llm-streaming.md
TurnTriggerMap	dsh-session	TurnTrigger	session.md
TurnEndReasonMap	dsh-session	TurnEndReason	session.md
SessionEventMap	dsh-session	SessionEvent	session.md

Two large discriminated unions are the ones consumers switch over most: StreamChunk (the streaming protocol) and SessionEvent (the log entry). Per the repo convention, switch on the tag — don't chain ifs — so each arm narrows and a typo'd tag fails to compile.

Branded IDs

IDs passed between packages are branded — structurally strings, but non-interchangeable at the type level (a SessionId cannot be passed where a CallId is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings.

The Branded<B> primitive lives in its own type-only package, dsh-brand (no runtime code, no harness-package dependency), so any package can brand the ids it owns without depending on an unrelated capability package.

Source: packages/util/brand/src/index.ts

/** A string carrying a compile-time-only brand `B`. */
type Branded<B extends string> = string & { readonly [BRAND]: B }

The two core IDs are CallId (correlates a tool call with its result; dsh-llm) and SessionId (the shared live agent and durable session identity; dsh-session). Capability packages brand their own ids too, such as JobId in jobs.md.

Cordis API

Generated from source by scripts/gen-cordis-catalog.ts (verified fresh by pnpm run verify-cordis-catalog in doc-sync; regenerate with pnpm run gen-cordis-catalog) — this section is byte-identical in both language sides of the page. Signature blocks use a ts cordis-catalog fence and keep the original source JSDoc; dispatch modes are defined in the primer, and the framework-inherited ctx API lives in cordis-api/inherited.md.

ctx.agentDefaultModel — AgentDefaultModelConfig

Owns the default model selection independently of any Host or transport. The composition entry remains usable without a settings provider; when one is mounted, its user layer is read live.

/**
 * Read the current default model selection.
 * @returns a detached provider, model, and optional reasoning selection.
 */
currentSelection(): ModelSelection

/**
 * Save the complete default model selection. A deployment without a settings
 * provider keeps its composition entry.
 * @param next - resolved selection accepted by an entry point.
 * @returns fulfillment after the optional settings write settles.
 */
async saveSelection(next: ModelSelection): Promise<void>

Source: packages/core/agent-default-model/src/index.ts:64

ctx.agentLoop — AgentLoop

Concrete agent factory and driver service.

/**
 * Create an agent and session under one caller-supplied identity, owned by
 * the accessing fiber. Constructor-driven config calls mint a fresh combined
 * id before entering this boundary.
 * @param id - shared agent/session identity.
 * @param options - concrete loop options.
 * @param meta - optional fresh-session workspace metadata.
 * @returns the published running agent.
 */
create(id: SessionId, options: AgentOptions = {}, meta: Pick<SessionHeader, 'cwd'> = {}): Agent

/**
 * Create an owned agent on a caller-supplied session id.
 * @param ownerCtx - caller context that structurally owns the lifecycle.
 * @param options - identities, session seed/metadata, loop options, setup, and cancellation.
 * @returns the published handle.
 */
async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise<AgentHandle>

/**
 * Resume an owned agent from the configured persistence service.
 * @param ownerCtx - caller context that owns load, setup, and the live lifecycle.
 * @param options - persisted identity, loop options, setup, and cancellation.
 * @returns the published handle.
 */
async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise<AgentHandle>

Types: SessionHeader

Source: packages/core/agent-loop/src/index.ts:296

ctx.agentPresets — AgentPresets

Registry over the deployment's agent presets.

Discovery is unmemoized: list() and resolve() re-read the roots on every call so a preset authored while the process runs is visible immediately, and a preset deleted underneath a picker disappears from the next read.

/**
 * Every preset the configured roots currently supply.
 * @returns the presets, first-root-wins per id.
 */
async list(): Promise<AgentPreset[]>

/**
 * Resolve one preset by id.
 *
 * A broken preset resolves — deleting one, reading one, and reporting one
 * all need the row — and the mounting paths refuse it AFTER resolution
 * through {@link resolveMountable}.
 * @param id - the preset id, or `undefined` for {@link defaultId}.
 * @returns the resolved preset.
 * @throws when no configured root supplies that id.
 */
async resolve(id?: string): Promise<AgentPreset>

/**
 * Compose one agent from a preset: ensure the preset's standing mount, then
 * parent the agent's scope key to it so the mount's registrations and
 * listeners cover this agent.
 *
 * Call from the agent factory's `setup(agentCtx)`; a rejection there rolls
 * the agent creation back, so a broken preset never yields a half-composed
 * session.
 * @param agentCtx - the agent's scope context.
 * @param id - the preset id, or `undefined` for {@link defaultId}.
 * @returns the preset that was composed, for the caller to record.
 * @throws when the preset is unknown or its composition is unusable.
 */
async mount(agentCtx: Context, id?: string): Promise<AgentPreset>

/**
 * Join one agent to the SAME standing composition another already runs on.
 *
 * This is how a child agent inherits its parent's capabilities. It is a bind,
 * not a mount: the parent's generation is already composed, so the child gets
 * that exact instance — the same plugin objects, the same tool registrations,
 * the same prompt sections. Re-resolving the parent's preset by id instead
 * would re-read the roster, and a composition file edited since the parent
 * started would hand the child a DIFFERENT generation than the one its
 * parent's history was produced under (and a preset deleted since would fail
 * the child outright while its parent keeps running).
 *
 * Synchronous, and with no composition failure mode of its own — it reads no
 * roster, mounts nothing, and touches no file — which is what lets a child
 * creation window use it: the two in-process subagent drivers compose their
 * children inside a synchronous `setup`. It still rejects a caller error, as
 * the `@throws` below record.
 *
 * A parent that joined no preset — a rosterless deployment — yields no join
 * and no error: there, the model-facing rows sit in the host composition and
 * the child already sees them through the global layer.
 * @param agentCtx - the joining agent's scope context.
 * @param parentCtx - the scope context of the agent whose composition to join.
 * @returns the preset id joined, or undefined when the parent joined none.
 * @throws when `agentCtx` carries no scope, or has already joined a preset.
 */
composeFrom(agentCtx: Context, parentCtx: Context): string | undefined

/**
 * The preset one live agent runs on.
 *
 * Read from the live scope chain rather than from the session, so it answers
 * for an agent whose session has not recorded a preset yet — a child agent
 * whose durable header is being built from its parent's composition.
 * @param agentCtx - the agent's scope context.
 * @returns the preset id, or undefined when the agent joined none.
 */
composedPreset(agentCtx: Context): string | undefined

/**
 * Read one preset's composition text.
 * @param id - the preset id.
 * @returns the composition exactly as stored.
 * @throws when no configured root supplies that id.
 */
async read(id: string): Promise<string>

/**
 * Create a locally authored preset by copying an existing one whole.
 *
 * Copy is the only authoring write. Composition text never crosses this
 * seam: the source is named by id and its directory is copied as it stands,
 * so the copy is exactly as loadable as its source and authoring grants no
 * capability the roster did not already carry. The copy is NOT mounted to
 * validate — a source that mounts today yields a copy that mounts today.
 * @param from - the preset the copy starts from; shipped presets are the
 * primary source, so any trust is accepted.
 * @param id - the new preset's id, which becomes its directory name.
 * @param name - display name for the copy; absent falls back to the id.
 * @throws when the source is unknown, the id is unusable or already taken,
 * or the deployment configures no writable root.
 */
async copy(from: string, id: string, name?: string): Promise<void>

/**
 * Delete a locally authored preset.
 * @param id - the preset id.
 * @throws when the preset is unknown or ships with the deployment.
 */
async remove(id: string): Promise<void>

/**
 * One agent's instance of a service its preset mounted.
 *
 * A preset publishes services behind `isolate` realms, which are invisible
 * outside the group that declares them — including to the host. This is how a
 * caller holding the agent reads one anyway: a request that is ABOUT a
 * session but arrives from outside it, which is every browser RPC.
 *
 * Read addressing only. A host row that `inject`s a service cannot use this,
 * because injection resolves before any session exists and has no agent to
 * key by; such a service belongs on the host plane instead.
 * @param agent - the agent whose composition to look inside.
 * @param name - the service name as the preset's rows resolve it.
 * @returns the agent's instance, or undefined when its preset mounts none.
 */
serviceFor<K extends string & keyof Context>(agent: { ctx: Context }, name: K): Context[K] | undefined

/**
 * Re-link one agent to a different preset's standing composition.
 *
 * Only valid while the agent has produced nothing: swapping tools mid
 * conversation would leave logged tool calls the new composition cannot
 * make. The CALLER owns that check — this method does not read session
 * history.
 *
 * The swap is a parent re-link, not an unmount: standing mounts are shared
 * and permanent, so the old composition stays for its other agents and the
 * new one is ensured BEFORE the link moves. An unknown or unusable preset
 * therefore throws with the agent exactly as it was — there is no torn-down
 * state to restore. The re-link runs through the binding this roster kept
 * from the agent's mount — dsh-scope's only re-link authority. An agent
 * that never composed one has nothing to re-link: the switch is then the
 * agent's first bind, exactly a mount.
 * @param agentCtx - the agent's scope context.
 * @param id - the preset to compose the agent from instead.
 * @returns the preset now installed.
 * @throws when the preset is unknown or its composition is unusable.
 */
async recompose(agentCtx: Context, id: string): Promise<AgentPreset>

/**
 * The standing scope key of one preset, for a host reader with no agent.
 *
 * A cold transcript read resolves tool presenters against the composition
 * the session recorded, and the standing mount makes that possible without
 * resuming anything: ensuring the mount composes plugins but starts no
 * agent, no session, and no turn.
 * @param id - the preset id, or `undefined` for {@link defaultId}.
 * @returns the standing scope key readers pass as a registry view scope.
 * @throws when the preset is unknown or its composition is unusable.
 */
async standingKeyFor(id?: string): Promise<ScopeKey>

Types: ScopeKey

Source: packages/preset/agent-presets/src/index.ts:82

ctx.agents — AgentRegistry

Agent service (ctx.agents): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent creation is provided by whichever plugin implements the AgentFactory (@deepseek-ai/dsh-agent-loop), registered via setFactory.

Initiator methods provide same-process causal attribution only. Ambient presence is neither liveness proof nor authorization; subjects and owners remain explicit, as does identity at worker, process, persistence, and wire boundaries. Returned Promise boundaries drain during teardown, except a nested lineage that starts an owning-fiber unload is excluded from its own drain.

/**
 * Read the Agent that initiated the inherited asynchronous driver chain.
 * Use this optional form for logging, tracing, metrics, or host attribution
 * that also supports agentless calls. When a parent creates a child, setup
 * reports the causal parent while `agentCtx.agent` identifies the child.
 * @returns the inherited Agent, or `undefined` outside an initiator boundary
 *   and inside an explicit clearing boundary.
 * @throws when this service instance has been disposed.
 */
currentInitiator(): Agent | undefined

/**
 * Read the initiating Agent and fail when no initiator boundary is active.
 * Use this for private helpers contractually below a driver, or for a
 * deployment-owned outbound request whose contract forbids agentless calls.
 * Generic or direct-call paths use optional lookup or explicit request fields.
 * @returns the inherited Agent.
 * @throws when no initiator is active or this service instance has been disposed.
 */
requireInitiator(): Agent

/**
 * Run an operation with one exact Agent as its process-local initiator. The
 * exact synchronous value or Promise returned by the operation is preserved.
 * Custom drivers and test harnesses wrap their complete returned foreground
 * lifetime.
 * A queue or wire receiver may establish this boundary only after validating
 * explicit identity and resolving the exact live Agent; this method does neither.
 * Detached work remains owned by the subsystem that starts it.
 * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization.
 * @param operation - synchronous or asynchronous operation to invoke.
 * @returns the exact value returned by `operation`.
 * @throws when the initiator scope is closing/disposed, or when `operation` throws.
 */
withInitiator<T>(agent: Agent, operation: () => T): T

/**
 * Run an operation inside a boundary that hides any inherited initiating
 * Agent. The exact synchronous value or Promise is preserved.
 * Use this while creating lazy shared timers, queue pumps, pool maintenance,
 * watchers, or exporters so they do not inherit the first Agent that happens
 * to initialize them. It clears only initiator attribution, not explicit
 * fields, and does not own or drain detached resources.
 * @param operation - synchronous or asynchronous operation to invoke without an initiator.
 * @returns the exact value returned by `operation`.
 * @throws when the initiator scope is closing/disposed, or when `operation` throws.
 */
withoutInitiator<T>(operation: () => T): T

/**
 * Register the agent-creation factory (the loop calls this on construction,
 * effect-scoped). A traced Cordis service is canonicalized to its concrete
 * target; each create/resume call is then traced through that caller's
 * context so ownership follows the caller without stacking proxy layers.
 * Throws if a factory is already registered. Returns the disposer; on
 * dispose the factory slot is cleared.
 * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to.
 * @returns the disposer that clears the factory slot. The exact
 *   Cordis effect disposer (single-shot): composite (generator) effects may
 *   yield it directly — exact identity nests the teardown in order.
 */
setFactory(factory: AgentFactory): () => void

/**
 * Create and publish a new agent through the registered factory.
 * Distinct from {@link register} (which records an already-constructed
 * agent): this constructs the agent and its session. Rejects if no factory is
 * registered or creation/setup fails. The resolved {@link AgentHandle} lets
 * the owner tear down exactly this agent.
 * @param options - shared identity, session seed/metadata, and agent options.
 * @returns the handle after setup, rollback-covered publication, and loop start complete.
 */
async create(options: CreateAgentOptions): Promise<AgentHandle>

/**
 * Load a persisted session and resume an agent on it through the registered
 * factory. Rejects if no factory is registered; the factory rejects if
 * session persistence is not configured or persistence/setup fails.
 * @param options - persisted identity, configuration, and optional setup.
 * @returns the handle after setup, rollback-covered publication, and loop start complete.
 */
async resume(options: ResumeAgentOptions): Promise<AgentHandle>

/**
 * Register a live agent. Throws if an agent with the same id is already
 * registered. Emits `agent/created` on registration and `agent/disposed`
 * when the calling fiber is disposed — both with the agent's scope carrier
 * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the
 * emits are scope-filtered regardless of which context invoked `register`
 * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always
 * requires passing the carrier). Returns the disposer.
 * @param agent - the already-constructed agent to record in the store.
 * @returns the EXACT Cordis effect disposer (single-shot; a repeat call
 *   returns undefined without awaiting an in-flight teardown). Exact
 *   identity is load-bearing: a composite (generator) effect that owns a
 *   teardown ORDER — the agent factory's lifecycle chain — must yield THIS
 *   function so Cordis nests the unregistration at that yield position;
 *   yielding a wrapper would leave it disposing as a concurrent sibling on
 *   owner unload, unregistering the agent (and emitting `agent/disposed`)
 *   while its final turn is still draining.
 */
register(agent: Agent): () => void

/**
 * Insert an already-constructed agent without announcing it. This is the
 * advanced ordered-lifecycle primitive used by the async agent factory: it
 * first completes setup while the agent is unpublished, then assigns the
 * returned detach closure into its pre-installed composite teardown before
 * calling {@link announce}. Ordinary callers use {@link register}.
 * @param agent - the prepared, unpublished agent.
 * @param owner - live agent whose scoped context created this agent, or
 *   undefined for a top-level runtime root. This is runtime ownership, not
 *   the resumed session's durable parent lineage.
 * @returns an idempotent closure that removes this exact entry and emits
 *   `agent/disposed` with listener failures contained. When called from a
 *   synchronous `agent/created` listener, removal and disposal wait until
 *   that creation dispatch unwinds.
 */
enter(agent: Agent, owner: Agent | undefined): () => void

/**
 * Announce an agent previously inserted with {@link enter}.
 * @param agent - the live inserted agent to announce.
 * @throws if `agent` is not the exact live registry entry for its id, or its
 *   creation announcement already began (including a reentrant call from a
 *   creation listener).
 */
announce(agent: Agent): void

/**
 * Look up a live agent.
 * @param id - the shared agent/session id to look up.
 * @returns the agent, or undefined when no live agent has that id.
 */
get(id: SessionId): Agent | undefined

/**
 * Test whether a live agent was created through one exact parent agent's
 * scoped context. Runtime ownership is independent of durable session
 * lineage and remains unambiguous when unrelated providers reuse an id.
 * @param id - the candidate child agent's shared agent/session id.
 * @param owner - the expected runtime creator agent.
 * @returns true only while the exact child entry is live under that owner.
 */
isOwnedBy(id: SessionId, owner: Agent): boolean

/**
 * All live agents, in registration order.
 * @returns a fresh array; mutating it does not affect the registry.
 */
list(): Agent[]

/**
 * All live top-level agents in registration order. A top-level agent was
 * created without an owning agent context; durable session lineage does not
 * affect this runtime relation, so a resumed fork may still be a root.
 * @returns a fresh array; mutating it does not affect the registry.
 */
roots(): Agent[]

Source: packages/core/agent/src/index.ts:256

agent/* events

agent/created — emit

A fully configured agent and live session were published. Setup is composition-only; agent/session-start is the first startup-driving extension point. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry.

/**
 * A fully configured agent and live session were published. Setup is
 * composition-only; `agent/session-start` is the first startup-driving extension point.
 * Synchronous listener failure vetoes publication, while returned-promise
 * rejection is reported. Detach requested during dispatch waits until every
 * creation listener has observed the stable entry.
 * @param payload.agent - the newly registered agent with its live session and completed setup.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/created'(this: Scoped<Agent>, payload: { agent: Agent }): void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:159

agent/disposed — emit

An agent left the registry; AgentLoop emits this after driver quiescence and scoped-registration unwind, but before session detachment. Custom registry users own their driver-ordering contract.

/**
 * An agent left the registry; AgentLoop emits this after driver quiescence
 * and scoped-registration unwind, but before session detachment. Custom
 * registry users own their driver-ordering contract.
 * @param payload.agent - the exact agent removed from the registry.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/disposed'(this: Scoped<Agent>, payload: { agent: Agent }): void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:168

agent/error — emit

A step or turn errored. The machine reports a failure here even when the error has no in-turn position for a durable record.

/**
 * A step or turn errored. The machine reports a failure here even when
 * the error has no in-turn position for a durable record.
 * @param payload.agent - the agent whose turn errored.
 * @param payload.turn - the turn in which the failure surfaced.
 * @param payload.step - the step at which the failure surfaced.
 * @param payload.error - the failure, verbatim.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/error'(this: Scoped<Agent>, payload: { agent: Agent; turn: number; step: number; error: unknown }): void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:290

agent/inbox/claimed — emit

One message left the inbox inside its open turn. If the proposed step is rejected, the claimed message ends here: it is neither discarded nor re-emitted as a user/message, and the turn closes without a step.

/**
 * One message left the inbox inside its open turn. If the proposed step
 * is rejected, the claimed message ends here: it is neither discarded nor
 * re-emitted as a user/message, and the turn closes without a step.
 * @param payload.agent - the agent whose inbox changed.
 * @param payload.message - the claimed message.
 * @param payload.turn - the owning turn.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/inbox/claimed'(this: Scoped<Agent>, payload: { agent: Agent; message: UserMessage; turn: number }): void

Types: Scoped · UserMessage

Source: packages/core/agent/src/runtime-types.ts:197

agent/inbox/discarded — emit

One message was discarded from the live inbox.

/**
 * One message was discarded from the live inbox.
 * @param payload.agent - the agent whose inbox changed.
 * @param payload.message - the discarded message.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/inbox/discarded'(this: Scoped<Agent>, payload: { agent: Agent; message: UserMessage }): void

Types: Scoped · UserMessage

Source: packages/core/agent/src/runtime-types.ts:205

agent/inbox/inserted — emit

One message entered the live inbox.

/**
 * One message entered the live inbox.
 * @param payload.agent - the agent whose inbox changed.
 * @param payload.message - the inserted message.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/inbox/inserted'(this: Scoped<Agent>, payload: { agent: Agent; message: UserMessage }): void

Types: Scoped · UserMessage

Source: packages/core/agent/src/runtime-types.ts:186

agent/pre-step — waterfall

Reject a proposed step or replace the messages that enter it. Calling next() preserves the current messages.

/**
 * Reject a proposed step or replace the messages that enter it. Calling
 * `next()` preserves the current messages.
 * @param payload.agent - the agent proposing the step.
 * @param payload.messages - messages removed from the inbox for this step.
 * @param payload.turn - the turn that will own the step.
 * @param payload.step - the step proposed by the loop.
 * @param payload.signal - the current turn's cancellation signal.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode waterfall
 */
'agent/pre-step'(this: Scoped<Agent>, payload: { agent: Agent; messages: UserMessage[]; turn: number; step: number; signal: AbortSignal }, next: () => Promise<PreStepDecision>): Promise<PreStepDecision>

Types: Scoped · UserMessage

Source: packages/core/agent/src/runtime-types.ts:231

agent/request — waterfall

Replace the frozen call configuration. await next() yields the config the machine would use (agent options on the first request, the logged header afterwards); return a replacement to switch. Model-visible content must use logged channels; this waterfall cannot mutate messages.

/**
 * Replace the frozen call configuration. `await next()` yields the config
 * the machine would use (agent options on the first request, the logged
 * header afterwards); return a replacement to switch. Model-visible
 * content must use logged channels; this waterfall cannot mutate messages.
 * @param payload.agent - the agent making the model call.
 * @param payload.turn - the open turn number.
 * @param payload.step - the step whose request this is.
 * @param payload.signal - the current turn's explicit abort signal.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode waterfall
*/
'agent/request'(this: Scoped<Agent>, payload: { agent: Agent; turn: number; step: number; signal: AbortSignal }, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>

Types: LlmCallConfig · Scoped

Source: packages/core/agent/src/runtime-types.ts:244

agent/request-error — waterfall

Handle one failed model-request attempt before the loop retries or closes its step. A listener returns { kind: 'retry' } without calling next() when it owns recovery, or calls next() to delegate. The default undefined leaves the failure terminal.

/**
 * Handle one failed model-request attempt before the loop retries or closes
 * its step. A listener returns `{ kind: 'retry' }` without calling `next()`
 * when it owns recovery, or calls `next()` to delegate. The default
 * `undefined` leaves the failure terminal.
 * @param payload.agent - the agent whose request failed.
 * @param payload.turn - the turn containing the failed request.
 * @param payload.step - the step containing the failed request attempt.
 * @param payload.provider - the provider selected for the failed request.
 * @param payload.failure - serializable facts normalized at the final adapter boundary.
 * @param payload.retryPolicy - the policy of the adapter registration that served the failed request.
 * @param payload.signal - the turn abort signal.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode waterfall
 */
'agent/request-error'(this: Scoped<Agent>, payload: { agent: Agent; turn: number; step: number; provider: string; failure: LlmFailure; retryPolicy: ResolvedRetryPolicy | undefined; signal: AbortSignal }, next: () => Promise<RequestErrorAction>): Promise<RequestErrorAction>

Types: LlmFailure · ResolvedRetryPolicy · Scoped

Source: packages/core/agent/src/runtime-types.ts:260

agent/session-start — emit

The session lifecycle began, once before the first turn. Use agent.inject() to seed model-facing context. This is a notification, not a veto; disposal requested by a lifecycle owner is rechecked before the driver starts.

/**
 * The session lifecycle began, once before the first turn. Use
 * `agent.inject()` to seed model-facing context. This is a notification, not
 * a veto; disposal requested by a lifecycle owner is rechecked before the
 * driver starts.
 * @param payload.agent - the agent whose session lifecycle began.
 * @param payload.source - why the session started (fresh startup, resume, …).
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/session-start'(this: Scoped<Agent>, payload: { agent: Agent; source: SessionStartSource }): void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:217

agent/status — emit

Agent status changed (idle ⇄ running). A waking delivery enters running synchronously after reserving cancellation; idle means no driver remains scheduled or active.

/**
 * Agent status changed (`idle` ⇄ `running`). A waking delivery enters
 * `running` synchronously after reserving cancellation; `idle` means no
 * driver remains scheduled or active.
 * @param payload.agent - the agent whose status flipped.
 * @param payload.status - the status just entered (the transition's destination).
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode emit
 */
'agent/status'(this: Scoped<Agent>, payload: { agent: Agent; status: AgentStatus }): void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:178

agent/turn-stopping — serial

The turn is about to close: the model owes no response (no live tool calls, no fresh steering). Awaited before the boundary commits — a listener that objects steers (agent.steer(...)) and the machine re-reads its inbox: fresh steering runs another step, none closes the turn. Data decides, so listener order cannot change the outcome. The inverse control (stop a tool loop early) is data too: a tool result carrying concludesTurn ends the turn at its step. The conclusion never short-circuits already-submitted next-step work: same-step additionalContexts or racing steering still runs, and the turn closes only when that inbox drains.

/**
 * The turn is about to close: the model owes no response (no live tool
 * calls, no fresh steering). Awaited before the boundary commits — a
 * listener that objects steers (`agent.steer(...)`) and the machine
 * re-reads its inbox: fresh steering runs another step, none closes the
 * turn. Data decides, so listener order cannot change the outcome. The
 * inverse control (stop a tool loop early) is data too: a tool result
 * carrying `concludesTurn` ends the turn at its step. The conclusion
 * never short-circuits already-submitted next-step work: same-step
 * `additionalContexts` or racing steering still runs, and the turn
 * closes only when that inbox drains.
 * @param payload.agent - the agent whose turn is at its stop boundary.
 * @param payload.turn - the turn about to close.
 * @param payload.signal - the current turn's explicit abort signal.
 * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
 * @mode serial
 */
'agent/turn-stopping'(this: Scoped<Agent>, payload: { agent: Agent; turn: number; signal: AbortSignal }): Promise<void> | void

Types: Scoped

Source: packages/core/agent/src/runtime-types.ts:278

agent-loop/* events

agent-loop/config-start-failed — emit

A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt.

/**
 * A declarative agent entry failed before it could publish a live agent.
 * Consumers that buffer work for the configured identity use this
 * transient signal to reject that work instead of waiting forever. Normal
 * factory teardown suppresses failures from the cancelled startup attempt.
 * @param payload.sessionId - exact shared agent/session identity that failed startup.
 * @param payload.error - persistence, setup, or publication failure.
 * @mode emit
 */
'agent-loop/config-start-failed'(payload: { sessionId: SessionId; error: unknown }): void

Source: packages/core/agent-loop/src/index.ts:183

agent-preset/* events

agent-preset/selected — emit

One session committed a different agent preset to its durable log. Consumers invalidate only state derived from that session's composition.

/**
 * One session committed a different agent preset to its durable log.
 * Consumers invalidate only state derived from that session's composition.
 * @mode emit
 * @param sessionId - the session whose composition changed.
 * @param agentPreset - the preset recorded by the committed selection.
 */
'agent-preset/selected'(sessionId: SessionId, agentPreset: string): void

Source: packages/preset/agent-presets/src/types.ts:13