Workflow
The workflow seam lets an agent run a model-written orchestration SCRIPT that starts subagents. Like subagent it is one optional capability, not part of the agent loop, so its types and operations live here rather than in core.md. Like bash, it permits ONE engine implementation per context to provide ctx.workflowEngine; there is no named-provider registry (a second engine replaces the first through plugin configuration rather than running beside it).
Service Definition: dsh-workflow (ctx.workflowEngine + the vocabulary below). The Service Provider is dsh-workflow-worker-thread (a node:worker_threads engine — one worker per run, the script's vm context inside it); the model-facing Consumer is dsh-tool-workflow. The proposal and rationale: the dynamic-workflows Agent Note.
Sources: browser-safe vocabulary in packages/workflow/workflow/src/types.ts, Host request and live-run handles in runtime-types.ts.
The start request
What a caller asks for when starting a run. The ordinary workflow tool builds this from the model's { script, meta, args } call plus the calling agent; specialized consumers may also select one engine-wide subagentProvider and lower maxTotalAgents for the run, but the script cannot observe or replace either policy. meta and args are plain JSON DATA (the engine validates meta against its schema and rejects loud BEFORE anything runs — no script text is ever evaluated to obtain it). parent is REQUIRED — every child the script starts is attributed to it, and cwd, lineage, and depth pass through the subagent seam.
/**
* What a caller asks for when starting a workflow run. `meta` and `args` are
* plain JSON data by the seam contract. `parent` is required because every
* `agent()` spawned by the script is attributed to that live Agent.
*/
interface WorkflowStartRequest {
/** The plain-JS script body (top-level await allowed; ends with `return <json-value>`). */
script: string
/** The workflow's identity block, as plain JSON data (shape-validated by the engine). */
meta: WorkflowMeta
/** Optional input exposed verbatim to the script as the `args` global. */
args?: unknown
/** Optional engine-wide child-provider override for this run. */
subagentProvider?: string
/** Optional per-run total-child ceiling. */
maxTotalAgents?: number
/** The agent on whose behalf the run executes (parent of every child). */
parent: Agent
/** Cancels the run when aborted. */
signal?: AbortSignal
}The workflow's identity: WorkflowMeta
The identity block carried as data on the start request (the tool's meta parameter; the field vocabulary matches the Claude Code dynamic-workflows meta block). phases is progress vocabulary only: phase() calls match titles for observers; no execution structure is implied.
/**
* The script's identity block, provided as plain JSON data alongside the
* script body (the model-facing tool carries it as its `meta` parameter) and
* validated by the engine before the body runs. `name`/`description` are
* required; the rest is optional annotation. The field vocabulary matches the
* Claude Code dynamic-workflows meta block.
*/
interface WorkflowMeta {
/** Short kebab-case workflow name (display + persistence key). */
name: string
/** One-line description of what the workflow does. */
description: string
/** Optional guidance on when this workflow applies (shown in listings). */
whenToUse?: string
/** Optional phase declarations matched by `phase()` calls. */
phases?: WorkflowPhase[]
}The terminal result: WorkflowResult
The outcome of one run, resolved by WorkflowRun.result. value is the script's materialized return value — plain host-realm JSON data (null when the script returned nothing) — meaningful only for completed. stopReason is a CLOSED union (engine-owned; consumers may exhaust it): completed | cancelled | error. A non-completed reason carries the failure in error, and the consumer maps it to an isError tool result rather than reporting partial output as success.
/**
* The outcome resolved by a live workflow run. `value` is
* the script's materialized return value (plain host-realm JSON data; `null`
* when the script returned `undefined`) — meaningful only for `completed`.
* A non-`completed` reason carries the failure in `error`; the consumer maps
* it to an `isError` tool result rather than reporting partial output.
*/
interface WorkflowResult {
/** The script's return value (host JSON data; `null` for no return). */
value: unknown
/** Why the run settled. */
stopReason: WorkflowStopReason
/** The failure message (present iff `stopReason` is not `completed`). */
error?: string
/**
* How many `agent()` calls the run accepted over its whole lifetime. On a
* graceful settlement this is the script-side count (calls still queued for
* a concurrency slot included); on a termination path (grace force-settle,
* worker death) it degrades to the host-observed count — calls queued
* inside a terminated script are unknowable then.
*/
agentsStarted: number
}A live run: WorkflowRun
The handle the consumer holds while a script executes. The consumer awaits result, may cancel mid-flight, and MUST dispose on every path. result does NOT reject — a script failure resolves with stopReason: 'error' — and once the run is cancelled it SETTLES within the engine's bounded grace even if the script itself never settles (the engine force-settles cancelled; the worker-thread engine then terminates the script's worker), so a consumer awaiting result is never wedged past a cancellation. dispose() = cancel + that bounded settle + child quiescence; it never hangs on a stuck script.
/**
* Holder-owned live workflow. `result` never rejects; consumers may cancel
* and must call idempotent `dispose()` to await script and child quiescence.
*/
interface WorkflowRun {
readonly id: WorkflowRunId
/** The validated meta block available before the script body runs. */
readonly meta: WorkflowMeta
readonly result: Promise<WorkflowResult>
/** Cancel the run and its children. */
cancel(reason?: string): void
/** Cancel if needed and await bounded settlement and cleanup. */
dispose(): Promise<void>
}Failure discipline: WorkflowError.fatal
Hook misuse inside a script — bad arguments, unknown/deferred agent() options, a schema outside the structured-output subset, a tripped cap, a seam start failure, cancellation — throws a WorkflowError with fatal: true. The parallel()/pipeline() combinators RE-THROW fatal errors instead of mapping the item to null: a typo'd option must kill the script loudly, never dissolve into something that reads as an ordinary child failure. The per-item null is reserved for child-run failures (a non-completed stop reason) and ordinary in-stage script errors.
Events
The workflow/* events (workflow/start, workflow/phase, workflow/log, workflow/agent-start, workflow/agent-end, workflow/end — see the events catalog) are observe-only emits carrying DATA SNAPSHOTS: every payload starts with WorkflowRunInfo (id + meta), never the live WorkflowRun, so a subscriber cannot gain cancel/dispose, and workflow/end deliberately omits the result value (a listener observing outcomes must not receive a mutable alias of the caller's result). Every emit is per-listener contained — a throwing subscriber is logged, never propagated, and cannot starve the listeners registered after it — and every listener receives its own payload clone, so mutating it corrupts neither the engine nor other listeners; the containment mirrors subagent/start/subagent/end.
Durable Chat records
The top-level dsh-tool-workflow consumer projects display facts into its calling parent Session without changing execution ownership. It writes tool-workflow/run-start after a run is accepted, pairs member start and end by runId + seq, and writes tool-workflow/run-end only after the result is known and disposal reaches quiescence. Nested transport calls write no record. The first append failure disables later writes for that run, so the log remains empty or a legal continuous prefix and the tool result is unchanged.
dsh-tool-workflow/invariant validates the same protocol before live commit and when a Session is loaded: one start per run, positive unique member sequences, paired member endings, no run ending with open members, and no updates after the run ending. A missing member ending or run ending at the log tail is valid interruption evidence rather than corruption.
dsh-client-ui-workflow-run folds the four events through the Conversation Node engine into one workflow-run Chat node anchored at the run-start sequence, after the original workflow tool node. Phase groups come only from actual member starts and preserve exact strings, including the distinction between an omitted phase and ''. Closed Locations turn missing terminal facts into interrupted presentation. The UI package README owns disclosure, status, and same-parent local navigation behavior.
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.workflowEngine — WorkflowEngine (abstract seam)
Workflow Service Definition contract. Invalid requests throw before publication; a live run is holder-owned, its result never rejects, cancellation and disposal are bounded, and disposal waits for child cleanup within that bound. Lifecycle listener failures are contained, and workflow/end fires exactly once as the result settles.
/**
* Parse and execute a workflow script.
* @param request - the script, its `args`, the parent agent, and an
* optional cancel signal.
* @returns the live run; its `result` resolves when the script settles.
*/
abstract start(request: WorkflowStartRequest): WorkflowRunSource: packages/workflow/workflow/src/index.ts:157
workflow/* events
workflow/agent-end — emit
One agent() call settled (clean result, child failure, or run cancellation). Paired with Events['workflow/agent-start'] by agent.seq, exactly once per started call on every stop path — on an engine termination path (a worker killed past its grace) the end is engine-synthesized with outcome 'cancelled'.
/**
* One `agent()` call settled (clean result, child failure, or run
* cancellation). Paired with {@link Events['workflow/agent-start']} by
* `agent.seq`, exactly once per started call on every stop path — on an
* engine termination path (a worker killed past its grace) the end is
* engine-synthesized with outcome `'cancelled'`.
* @param info - the run's identity snapshot.
* @param agent - the call identity plus its outcome.
* @mode emit
*/
'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): voidSource: packages/workflow/workflow/src/index.ts:79
workflow/agent-start — emit
One agent() call established a published child run. Paired with Events['workflow/agent-end'] by agent.seq. A call that never receives a published run from the provider emits neither event in this pair.
/**
* One `agent()` call established a published child run. Paired with
* {@link Events['workflow/agent-end']} by `agent.seq`. A call that never
* receives a published run from the provider emits neither
* event in this pair.
* @param info - the run's identity snapshot.
* @param agent - the call's sequence number, label, phase, and child id.
* @mode emit
*/
'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): voidSource: packages/workflow/workflow/src/index.ts:68
workflow/end — emit
A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves. Paired with Events['workflow/start'].
/**
* A workflow run settled (any stop reason). Fired when
* {@link WorkflowRun.result} resolves. Paired with
* {@link Events['workflow/start']}.
* @param info - the run's identity snapshot.
* @param result - the outcome data (stop reason, error, agent count) —
* deliberately WITHOUT the result value (see {@link WorkflowResultInfo}).
* @mode emit
*/
'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): voidSource: packages/workflow/workflow/src/index.ts:89
workflow/log — emit
The script emitted a narration line (a log(message) call).
/**
* The script emitted a narration line (a `log(message)` call).
* @param info - the run's identity snapshot.
* @param message - the logged message, verbatim.
* @mode emit
*/
'workflow/log'(info: WorkflowRunInfo, message: string): voidSource: packages/workflow/workflow/src/index.ts:58
workflow/phase — emit
The script entered a phase (a phase(title) call) — progress grouping for observers; no execution semantics.
/**
* The script entered a phase (a `phase(title)` call) — progress grouping
* for observers; no execution semantics.
* @param info - the run's identity snapshot.
* @param title - the phase title, verbatim.
* @mode emit
*/
'workflow/phase'(info: WorkflowRunInfo, title: string): voidSource: packages/workflow/workflow/src/index.ts:51
workflow/start — emit
A workflow run started — the script's meta block validated, the body about to execute. Paired with Events['workflow/end'].
/**
* A workflow run started — the script's meta block validated, the body
* about to execute. Paired with {@link Events['workflow/end']}.
* @param info - the run's identity snapshot (id + meta).
* @mode emit
*/
'workflow/start'(info: WorkflowRunInfo): void