deepseek-harness/packages/workflow/workflow-worker-thread/src/runtime.ts

489 lines
22 KiB
TypeScript
Raw Normal View History

workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
/**
2026-08-09 15:27:21 +08:00
* Per-run worker-side vm hooks, child RPC, concurrency/caps, cancellation, and result serialization; it
* never touches Cordis. Script values leaving the realm are materialized as plain JSON before
* messaging. Values entering the trusted model-written realm are passed directly; `args` alone is
* cloned so script mutation cannot alter initialization data. See `./realm.ts` for the trust model.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*
* Fatal workflow errors—bad hook arguments, unsupported schemas/options, caps, start failures, and
* cancellation—propagate through combinators. Only child failures and ordinary stage errors become
* per-item nulls. Every returned promise has a rejection consumer so dropped script promises cannot
* kill the worker. A cancelled script that never settles emits nothing; the host force-settles the
* run within grace and terminates the thread.
* @module @deepseek-ai/dsh-workflow-worker-thread/runtime
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*/
import * as vm from 'node:vm'
import { brandString } from '@deepseek-ai/dsh-brand'
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { SessionId } from '@deepseek-ai/dsh-session'
2026-07-21 01:11:55 +08:00
import { assertObjectJsonSchema, JsonSchemaError } from '@deepseek-ai/dsh-tools'
import type { ObjectJsonSchema } from '@deepseek-ai/dsh-tools'
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
import { isFatalWorkflowError, WorkflowError } from '@deepseek-ai/dsh-workflow'
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
import type {
WorkflowAgentEndInfo,
WorkflowAgentInfo,
WorkflowMeta,
WorkflowResult,
} from '@deepseek-ai/dsh-workflow'
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
import { materializeFromRealm, MaterializeError, renderThrown } from './realm.ts'
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
import type { ChildHandle, ChildPort, WorkerLimits } from './types.ts'
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
/** The observers the execution reports progress through (the session posts them to the host). */
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
export interface ExecutionObserver {
phase(title: string): void
log(message: string): void
agentStart(info: WorkflowAgentInfo): void
agentEnd(info: WorkflowAgentEndInfo): void
}
/** The `agent()` options the script may pass; everything else rejects loud. */
2026-07-14 21:57:52 +08:00
const SUPPORTED_AGENT_OPTIONS = new Set(['label', 'phase', 'schema', 'provider', 'model'])
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
/** Deferred Claude Code options we name explicitly in the rejection message. */
const DEFERRED_AGENT_OPTIONS = new Set(['effort', 'isolation', 'agentType'])
/** Flatten a child's final output blocks to text (the non-schema `agent()` result). */
function outputText(blocks: ContentBlock[]): string {
return blocks
.filter((block): block is Extract<ContentBlock, { type: 'text' }> => block.type === 'text')
.map(block => block.text)
.join('')
}
/** A short display label derived from the prompt when the script passes none. */
function defaultLabel(prompt: string): string {
const newline = prompt.indexOf('\n')
const line = newline === -1 ? prompt : prompt.slice(0, newline)
return line.length <= 48 ? line : `${line.slice(0, 47)}…`
}
/**
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
* One live script execution inside the worker. Constructed per run by the
* session; `drive()` is called exactly once and NEVER rejects — every failure
* becomes a {@link WorkflowResult} with a non-`completed` stop reason. The
* host owns cancellation and cleanup of any dropped child work.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*/
export class WorkflowExecution {
/** 1-based count of `agent()` calls started (the `agentsStarted` result field). */
private started = 0
private activeSlots = 0
private readonly slotWaiters: { resolve(): void; reject(error: unknown): void }[] = []
private cancelReason: string | undefined
private cancelError: WorkflowError | undefined
private currentPhase: string | undefined
private readonly context: vm.Context
private readonly compiled: vm.Script
constructor(
meta: WorkflowMeta,
body: string,
args: unknown,
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
private readonly limits: WorkerLimits,
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
private readonly observer: ExecutionObserver,
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
private readonly children: ChildPort,
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
) {
// Compile FIRST: a body syntax error must throw out of the constructor
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// before any realm state exists. The host pre-parses the identical
// wrapper, so under one Node version this throw is unreachable in
// production — the session still maps it to an error result defensively.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
// lineOffset compensates for the wrapper line, so stack traces carry the
2026-07-09 20:09:10 +08:00
// script's own line numbers.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
try {
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
this.compiled = new vm.Script(`(async () => {\n${body}\n})()`, {
filename: `workflow:${meta.name}`,
lineOffset: -1,
})
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
} catch (error: unknown) {
throw new WorkflowError(`workflow script does not parse: ${String(error)}`, 'SCRIPT_PARSE', { cause: error })
}
this.context = vm.createContext({}, { name: `workflow:${meta.name}` })
const globals: Record<string, unknown> = {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
agent: (prompt: unknown, opts?: unknown) => this.contain(this.agent(prompt, opts)),
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
parallel: (thunks: unknown) => this.contain(this.parallel(thunks)),
pipeline: (items: unknown, ...stages: unknown[]) => this.contain(this.pipeline(items, stages)),
phase: (title: unknown) => { this.phase(title) },
log: (message: unknown) => { this.log(message) },
// workerData already performed the real cross-thread structured clone.
args,
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
for (const [key, value] of Object.entries(globals)) {
// Data properties on the contextified global; frozen shape not required —
// a script overwriting its own hooks only sabotages itself.
;(this.context as Record<string, unknown>)[key] = typeof value === 'function' ? Object.freeze(value) : value
}
}
/**
* Whether the run has been cancelled. A METHOD, not an inline property
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
* read: `cancel()` mutates `cancelReason` concurrently (the session's
* message handler), and an inline read after an `await` gets narrowed by
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
* control flow into an always-false comparison.
*/
private isCancelled(): boolean {
return this.cancelReason !== undefined
}
/**
* Shared hook entry guard: after {@link cancel}, EVERY hook throws
* `CANCELLED` at its next call — cancellation is the next HOOK boundary,
* not just the next `agent()`, so a script that caught one cancelled
* rejection cannot keep emitting progress through `phase`/`log` or enter a
* combinator.
*/
private throwIfCancelled(): void {
if (this.isCancelled()) throw this.cancelledError()
}
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
/**
* Cancel the run: waiting `agent()` slots reject and every future hook call
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
* throws `CANCELLED` — the script dies at its next await. A script that
* never settles anyway (parked on a promise no hook owns) is the HOST's
* problem: its grace timer force-settles the run and terminates the
* worker. Idempotent; the first reason wins.
* @param reason - human-readable cause carried on the CANCELLED error. The
* host independently aborts the required signal shared by every child.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*/
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
cancel(reason: string): void {
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (this.cancelReason !== undefined) return
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
this.cancelReason = reason
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
this.cancelError = new WorkflowError(`workflow run cancelled: ${this.cancelReason}`, 'CANCELLED')
for (const waiter of this.slotWaiters.splice(0)) waiter.reject(this.cancelledError())
}
/**
* Run the script to settlement. Resolves — never rejects — with the run's
* {@link WorkflowResult}: the materialized return value on `completed`, the
* failure message on `error`, and `cancelled` when the script died of
* cancellation. This method only chooses the result; the session publishes
* it and the host owns terminal child cancellation.
* @returns the settled outcome — this promise NEVER rejects (the seam's
* `result`-never-rejects contract); every failure maps to a variant.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*/
async drive(): Promise<WorkflowResult> {
try {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// Cancelled before the body ever ran (an already-aborted start signal,
// relayed by the host before its `go`): the script must not execute at
// all, let alone report `completed`.
2026-07-05 19:04:38 +08:00
if (this.isCancelled()) throw this.cancelledError()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
const scriptPromise = this.compiled.runInContext(this.context, { timeout: this.limits.syncTimeoutMs }) as Promise<unknown>
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
const raw: unknown = await this.contain(Promise.resolve(scriptPromise))
2026-07-05 19:04:38 +08:00
// Cancelled while the body ran: a script that settled without touching
// another hook (or without any) must still report `cancelled` — the
// holder asked for cancellation and `completed` would be a lie.
if (this.isCancelled()) throw this.cancelledError()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
const value = raw === undefined ? null : this.materializeResult(raw)
return { value, stopReason: 'completed', agentsStarted: this.started }
} catch (error: unknown) {
workflow: hook promises and hook failures are realm-built too Codex code-review round 5: agent()/parallel()/pipeline() returned HOST Promise objects into the script realm — Object.getPrototypeOf(agent('x')) reached host Promise.prototype, contradicting the realm contract (correctness containment, not the accepted sandbox stance). The rejection channel had the same leak one hop away: a caught hook failure was a host WorkflowError (host Error.prototype chain), and phase()/log() threw host errors synchronously. All three surfaces are realm-built now: - hook promises: the realm's own Promise.resolve (bound at context setup) assimilates the host promise, so the script-visible promise carries realm prototypes; the realm promise gets the same no-op rejection consumer as the host one (a script may drop it). - hook failures: rejections and phase/log sync throws are translated at the boundary into realm-built clones (name/code/message/fatal via an in-realm factory); non-WorkflowError host failures become generic realm Errors carrying their describeThrown rendering. - the combinators recognize FATAL clones structurally (isFatalWorkflowErrorClone: proxy-guarded descriptor reads), preserving the fatal-vs-null discipline across the boundary; a script forging the shape kills only its own run. drive() maps any post-cancel failure to 'cancelled' by run state (a CANCELLED clone deliberately fails the host instanceof). Tests: realm-promise identity for all three hooks + host Promise.prototype pollution unreachable; clone shape (instanceof realm Error, name/code/fatal/ message) with prototype-chain mutation staying realm-side; a rejecting provider result crossing as a generic clone; phase/log sync-throw clones; combinator catch branches (string throw, proxy throw, shape-miss forgery → null; forged fatal → kills own run); existing fatal-propagation, cancellation, and unhandled-rejection tests as canaries.
2026-07-05 21:24:30 +08:00
// Any failure after cancel() reports `cancelled` with the canonical
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
// reason — the reject path mirrors the resolve path's post-settle check.
workflow: hook promises and hook failures are realm-built too Codex code-review round 5: agent()/parallel()/pipeline() returned HOST Promise objects into the script realm — Object.getPrototypeOf(agent('x')) reached host Promise.prototype, contradicting the realm contract (correctness containment, not the accepted sandbox stance). The rejection channel had the same leak one hop away: a caught hook failure was a host WorkflowError (host Error.prototype chain), and phase()/log() threw host errors synchronously. All three surfaces are realm-built now: - hook promises: the realm's own Promise.resolve (bound at context setup) assimilates the host promise, so the script-visible promise carries realm prototypes; the realm promise gets the same no-op rejection consumer as the host one (a script may drop it). - hook failures: rejections and phase/log sync throws are translated at the boundary into realm-built clones (name/code/message/fatal via an in-realm factory); non-WorkflowError host failures become generic realm Errors carrying their describeThrown rendering. - the combinators recognize FATAL clones structurally (isFatalWorkflowErrorClone: proxy-guarded descriptor reads), preserving the fatal-vs-null discipline across the boundary; a script forging the shape kills only its own run. drive() maps any post-cancel failure to 'cancelled' by run state (a CANCELLED clone deliberately fails the host instanceof). Tests: realm-promise identity for all three hooks + host Promise.prototype pollution unreachable; clone shape (instanceof realm Error, name/code/fatal/ message) with prototype-chain mutation staying realm-side; a rejecting provider result crossing as a generic clone; phase/log sync-throw clones; combinator catch branches (string throw, proxy throw, shape-miss forgery → null; forged fatal → kills own run); existing fatal-propagation, cancellation, and unhandled-rejection tests as canaries.
2026-07-05 21:24:30 +08:00
if (this.isCancelled()) {
return { value: null, stopReason: 'cancelled', error: this.cancelledError().message, agentsStarted: this.started }
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// renderThrown is total (thrown values of any realm), so this arm
// cannot throw — drive() resolving is the `result` never-rejects contract
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// contract.
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
return { value: null, stopReason: 'error', error: renderThrown(error), agentsStarted: this.started }
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
}
/**
* Attach a no-op rejection consumer WITHOUT changing what the caller
* receives: if the script drops the promise (no await), cancellation cannot
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
* become an unhandled rejection (which would kill the worker thread); if
* the script does await it, it still observes the rejection.
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
*/
private contain<T>(promise: Promise<T>): Promise<T> {
promise.catch(() => { /* consumed: see method contract — a dropped hook promise must not surface an unhandled rejection */ })
return promise
}
private cancelledError(): WorkflowError {
// cancel() arms cancelError before any caller can observe isCancelled()
// === true; the fallback guards the type, not a reachable path.
/* v8 ignore next */
return this.cancelError ?? new WorkflowError('workflow run cancelled', 'CANCELLED')
}
/** Materialize the script's return value; violations become RESULT_UNSERIALIZABLE. */
private materializeResult(raw: unknown): unknown {
try {
return materializeFromRealm(raw, 'workflow result')
} catch (error: unknown) {
/* v8 ignore next -- defensive rethrow arm: materializeFromRealm only throws MaterializeError */
if (!(error instanceof MaterializeError)) throw error
throw new WorkflowError(
`the workflow's return value is not plain JSON data — ${error.message}. Return only JSON-serializable objects/arrays/scalars.`,
'RESULT_UNSERIALIZABLE',
{ cause: error },
)
}
}
/**
* Acquire one concurrency slot (FIFO). Cancellation rejects QUEUED waiters
* (see {@link cancel}); the callers guard their own entry and post-acquire
* windows, so no cancelled-precheck is duplicated here.
*/
private acquireSlot(): Promise<void> {
if (this.activeSlots < this.limits.maxConcurrentAgents) {
this.activeSlots += 1
return Promise.resolve()
}
return new Promise<void>((resolve, reject) => {
this.slotWaiters.push({
resolve: () => {
this.activeSlots += 1
resolve()
},
reject,
})
})
}
private releaseSlot(): void {
this.activeSlots -= 1
const next = this.slotWaiters.shift()
if (next) next.resolve()
}
/** The `agent(prompt, opts)` hook. */
private async agent(rawPrompt: unknown, rawOpts: unknown): Promise<unknown> {
this.throwIfCancelled()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (typeof rawPrompt !== 'string' || rawPrompt.length === 0) {
throw new WorkflowError('agent() requires a non-empty prompt string', 'INVALID_ARGUMENT')
}
const opts = this.readAgentOptions(rawOpts)
if (this.started >= this.limits.maxTotalAgents) {
throw new WorkflowError(
`this run reached its total agent cap (${this.limits.maxTotalAgents}) — a runaway-loop backstop; raise the applicable maxTotalAgents limit if the scale is intentional`,
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
'AGENT_CAP',
)
}
this.started += 1
const seq = this.started
const label = opts.label ?? defaultLabel(rawPrompt)
const phase = opts.phase ?? this.currentPhase
await this.acquireSlot()
try {
// Re-check after the acquire: the await yields at least one microtask
// tick even when a slot is free, and a queued waiter resumes a tick
// after its release — a cancel() landing in either window must not
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// reach the host (which would refuse anyway, but the refusal reads as
// a start failure rather than the cancellation it is).
this.throwIfCancelled()
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
let run: ChildHandle
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
try {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
run = await this.children.startAgent({
prompt: rawPrompt,
...opts.schema !== undefined ? { schema: opts.schema } : {},
2026-07-14 21:57:52 +08:00
...opts.provider !== undefined ? { provider: opts.provider } : {},
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
...opts.model !== undefined ? { model: opts.model } : {},
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
})
} catch (error: unknown) {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// The host refuses starts once the run is cancelled — a refusal that
// races our own cancel state must read as the cancellation it is,
// not as a broken contract.
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
if (this.isCancelled()) throw this.cancelledError()
throw new WorkflowError(`agent() could not start a child: ${renderThrown(error)}`, 'AGENT_START', { cause: error })
}
// The start round-trip yields to the event loop, so a cancel CAN land
// between the host starting the child and this continuation running —
// wind the fresh child down instead of leaving it live behind a dead
// script.
if (this.isCancelled()) {
await run.dispose()
throw this.cancelledError()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: brandString<SessionId>(run.id) }
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
this.observer.agentStart(info)
try {
let result
try {
result = await run.result
} catch (error: unknown) {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// A rejected child result is an INFRASTRUCTURE fault relayed by the
// host — distinct from a child that failed and resolved. Pair the
// lifecycle before propagating, and propagate FATAL: an ordinary
// throw would dissolve to a per-item null inside the combinators,
// and a broken provider must not read as a failed child.
if (this.isCancelled()) {
this.observer.agentEnd({ ...info, outcome: 'cancelled' })
throw this.cancelledError()
}
this.observer.agentEnd({ ...info, outcome: 'failed' })
throw new WorkflowError(`child agent run failed: ${renderThrown(error)}`, 'AGENT_RESULT', { cause: error })
}
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (result.stopReason === 'completed') {
if (opts.schema !== undefined) {
// The provider honored outputSchema (capability-gated at start), so
// a completed run without a structured value is a child failure.
if (result.structured === undefined) {
this.observer.agentEnd({ ...info, outcome: 'failed' })
return null
}
this.observer.agentEnd({ ...info, outcome: 'completed' })
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
return result.structured
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
this.observer.agentEnd({ ...info, outcome: 'completed' })
return outputText(result.output)
}
// A cancelled RUN kills the script; a child that failed for its own
// reasons resolves null (scripts .filter(Boolean) per the CC contract).
if (this.isCancelled()) {
this.observer.agentEnd({ ...info, outcome: 'cancelled' })
throw this.cancelledError()
}
this.observer.agentEnd({ ...info, outcome: 'failed' })
return null
} finally {
await run.dispose()
}
} finally {
this.releaseSlot()
}
}
/** Materialize + validate the `agent()` options bag from the realm. */
2026-07-14 21:57:52 +08:00
private readAgentOptions(rawOpts: unknown): {
label?: string
phase?: string
provider?: string
model?: string
2026-07-21 01:11:55 +08:00
schema?: ObjectJsonSchema
2026-07-14 21:57:52 +08:00
} {
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (rawOpts === undefined) return {}
let opts: unknown
try {
opts = materializeFromRealm(rawOpts, 'agent() options')
} catch (error: unknown) {
/* v8 ignore next -- defensive rethrow arm: materializeFromRealm only throws MaterializeError */
if (!(error instanceof MaterializeError)) throw error
throw new WorkflowError(`agent() options must be plain JSON data — ${error.message}`, 'INVALID_ARGUMENT', { cause: error })
}
if (typeof opts !== 'object' || opts === null || Array.isArray(opts)) {
throw new WorkflowError('agent() options must be an object', 'INVALID_ARGUMENT')
}
const record = opts as Record<string, unknown>
for (const key of Object.keys(record)) {
if (SUPPORTED_AGENT_OPTIONS.has(key)) continue
if (DEFERRED_AGENT_OPTIONS.has(key)) {
throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION')
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
2026-07-14 21:57:52 +08:00
throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION')
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
}
2026-07-14 21:57:52 +08:00
for (const key of ['label', 'phase', 'provider', 'model'] as const) {
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (record[key] !== undefined && typeof record[key] !== 'string') {
throw new WorkflowError(`agent() option "${key}" must be a string`, 'INVALID_ARGUMENT')
}
}
2026-07-21 01:11:55 +08:00
let schema: ObjectJsonSchema | undefined
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (record.schema !== undefined) {
try {
2026-07-21 01:11:55 +08:00
assertObjectJsonSchema(record.schema)
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
schema = record.schema
} catch (error: unknown) {
2026-07-21 01:11:55 +08:00
/* v8 ignore next -- defensive rethrow arm: assertObjectJsonSchema only throws JsonSchemaError */
if (!(error instanceof JsonSchemaError)) throw error
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
throw new WorkflowError(`agent() schema is outside the supported subset — ${error.message}`, 'UNSUPPORTED_SCHEMA', { cause: error })
}
}
return {
...record.label !== undefined ? { label: record.label as string } : {},
...record.phase !== undefined ? { phase: record.phase as string } : {},
2026-07-14 21:57:52 +08:00
...record.provider !== undefined ? { provider: record.provider as string } : {},
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
...record.model !== undefined ? { model: record.model as string } : {},
...schema !== undefined ? { schema } : {},
}
}
/** The `parallel(thunks)` hook: each thunk caught → `null`; fatal errors propagate. */
private async parallel(rawThunks: unknown): Promise<unknown[]> {
this.throwIfCancelled()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (!Array.isArray(rawThunks)) {
throw new WorkflowError('parallel() requires an array of zero-argument functions', 'INVALID_ARGUMENT')
}
this.assertItemCap(rawThunks.length, 'parallel()')
const thunks = rawThunks.map((thunk, index) => {
if (typeof thunk !== 'function') {
throw new WorkflowError(`parallel() item ${index} is not a function`, 'INVALID_ARGUMENT')
}
return thunk as () => unknown
})
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
return Promise.all(thunks.map(async (thunk) => {
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
try {
return await thunk()
} catch (error: unknown) {
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// Hook failures are WorkflowErrors built OUTSIDE the script's realm;
// fatality is recognized by `instanceof` against this realm's class —
// a script-built object can never pass it, so fatality cannot be
// forged (nor accidentally dissolved).
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
if (isFatalWorkflowError(error)) throw error
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
return null
}
}))
}
/** The `pipeline(items, ...stages)` hook: per-item stage chains, NO cross-stage barrier. */
private async pipeline(rawItems: unknown, rawStages: unknown[]): Promise<unknown[]> {
this.throwIfCancelled()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (!Array.isArray(rawItems)) {
throw new WorkflowError('pipeline() requires an items array', 'INVALID_ARGUMENT')
}
this.assertItemCap(rawItems.length, 'pipeline()')
if (rawStages.length === 0) {
throw new WorkflowError('pipeline() requires at least one stage function', 'INVALID_ARGUMENT')
}
const stages = rawStages.map((stage, index) => {
if (typeof stage !== 'function') {
throw new WorkflowError(`pipeline() stage ${index} is not a function`, 'INVALID_ARGUMENT')
}
return stage as (previous: unknown, item: unknown, index: number) => unknown
})
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
return Promise.all(rawItems.map(async (item: unknown, index) => {
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
let value: unknown = item
try {
for (const stage of stages) {
value = await stage(value, item, index)
}
return value
} catch (error: unknown) {
// An ordinary stage throw drops the ITEM to null and skips its
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
// remaining stages; a fatal WorkflowError (see parallel()) kills the
// whole script.
workflow: simplify to the trust premise; settle result on cancellation Two review responses that belong together — the same review argued the engine was defending the wrong threat while a benign-input bug wedged the product. 1) Drop hostile-value containment; state the trust premise. Scripts are model-written — the same trust level as the model's bash access — yet successive pre-push review rounds had ratcheted in defenses that only matter against an adversarial author: trap-free proxy rejection, accessor-never-invoked descriptor walks, realm-side pre-rendering of thrown values, realm-built promises/arrays/error clones with structural fatal recognition. That same author keeps a documented, accepted, unkillable event-loop spin, so containing its error VALUES is cost without a threat model — and the planned hardened engine (worker/isolated-vm) gets value isolation by serialization and deletes all of this machinery anyway. What stays, because benign scripts hit it constantly: result never rejects; dropped hook promises cannot become unhandled rejections; the value boundary rejects LOUD everything JSON cannot carry (now a plain recursive walk — getters are read ordinarily and their result is what crosses; a throwing read fails loud); a "__proto__" key still copies as a data property; the fatal-vs-null combinator discipline (now host instanceof — unforgeable from the realm and simpler than clone-shape recognition). What changes for scripts (documented in the engine README): hooks hand back host values and host errors — in-script `instanceof Error` on a hook failure is false (branch on e.name/e.code) — and args are host-cloned once so a script cannot mutate the caller's object. realm.ts drops 289 → 173 lines; the hostile-value test tables go with it. The premise now leads the engine module doc, the README, and the RFC's engine section, with the removed machinery recorded under What was rejected. 2) result settles within the dispose grace of a cancellation. Review finding (verified through the real registry + tool + engine): a script parked on a promise no hook owns — `await new Promise(() => {})`, `await Promise.race([])`, a returned never-settling thenable — could not be settled by cancel(): hooks reject and children abort, but nothing touches a promise the engine does not own, so `result` stayed pending FOREVER (the previous cut even pinned that as intended). The tool awaits run.result BEFORE its disposing finally, the registry awaits the tool, the loop awaits the registry — one such script wedged the whole agent turn past any abort, unrecoverable in-process; the mock engine in the tool's abort test settles result on cancel, which is exactly the behavior the real engine lacked, so no existing test could see it. The seam contract now says it out loud: once a run is cancelled, result SETTLES within the implementation's bounded grace even if the script never does. The vm engine arms an abandon channel in cancel(); drive() races the script against it, force-settling 'cancelled' at the grace (the abandoned settlement stays contained; a post-slice synchronous spin remains the documented limitation). dispose()'s outer race now exists for child quiescence only, and `workflow/end` again fires exactly once per started run. The old 'result stays pending' pin is FLIPPED to the new contract (the pinned behavior was the bug); new regressions cover cancel-then-settle on a parked script, a never-settling returned thenable, and the full composition through the REAL registry + tool + vm engine (tool-workflow gains workflow-vm/subagent devDeps for it). agentsStarted JSDoc clarified while touching the vocabulary (accepted calls, including ones still queued at cancellation).
2026-07-06 00:48:49 +08:00
if (isFatalWorkflowError(error)) throw error
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
return null
}
}))
}
private assertItemCap(length: number, hook: string): void {
if (length > this.limits.maxItemsPerCall) {
throw new WorkflowError(
`${hook} received ${length} items — over the per-call cap (${this.limits.maxItemsPerCall}); split the work or raise maxItemsPerCall in the engine config`,
'ITEM_CAP',
)
}
}
/** The `phase(title)` hook: sets the current label for subsequent `agent()` calls and notifies observers. */
private phase(title: unknown): void {
this.throwIfCancelled()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (typeof title !== 'string' || title.length === 0) {
throw new WorkflowError('phase() requires a non-empty title string', 'INVALID_ARGUMENT')
}
this.currentPhase = title
this.observer.phase(title)
}
/** The `log(message)` hook: narration to observers. */
private log(message: unknown): void {
this.throwIfCancelled()
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
if (typeof message !== 'string') {
throw new WorkflowError('log() requires a message string', 'INVALID_ARGUMENT')
}
this.observer.log(message)
}
}