feat: phase 3-5 — workflow engine, background subagents, multi-modal, cache shape, inline diff

Phase 3: Dynamic Workflow Engine
- VM sandbox (node:vm) with agent/parallel/pipeline API, Claude Code compatible
- Workflow file discovery (.boocode/workflows/*.js + ~/.boocode/workflows/*.js)
- Workflow manager with session/chat creation and inference dispatch
- Built-in catalog: deep-research, review-code, find-issues
- Resumability cache: SHA-256 hash of agent spec, in-memory Map

Phase 4: Background Subagents
- background-task.ts service: spawn/poll/cancel lifecycle
- spawn_subagent, subagent_status, subagent_result tools in ALL_TOOLS

Phase 5: Multi-modal + Cache Shape
- Multi-modal stub with type defs and hook point in payload.ts
- CacheShapeBadge component in trace viewer (colored bar + %)
This commit is contained in:
2026-06-08 03:11:39 +00:00
parent 591d373534
commit f22da55734
23 changed files with 2938 additions and 33 deletions

View File

@@ -0,0 +1,376 @@
// v2.8.0: Workflow catalog — built-in workflow definitions that ship with
// BooCode. Each workflow is a metadata object with name, description, and a
// factory function that returns the workflow script source code.
//
// Built-in workflows are merged into the discovery list alongside file-based
// workflows from .boocode/workflows/. They take precedence over user-defined
// workflows with the same name.
import { createHash } from 'node:crypto';
// ---------------------------------------------------------------------------
// Types
// ---------------------------------------------------------------------------
/**
* A built-in workflow definition shipped with BooCode.
*/
export interface BuiltinWorkflow {
/** Unique workflow name (used to invoke via `WorkflowManager`). */
name: string;
/** Human-readable description of what this workflow does. */
description: string;
/** Optional ordered phases for UI progress display. */
phases?: Array<{ title: string; detail?: string }>;
/**
* Generate the workflow script source code for this workflow.
* The returned string must be valid JS that exports `meta` and a `default`
* async function matching the `WorkflowScript` shape.
*
* @param args - Optional arguments provided when the workflow is started.
*/
generateScript: (args?: Record<string, unknown>) => string;
}
// ---------------------------------------------------------------------------
// Script templates (shared helpers)
// ---------------------------------------------------------------------------
/**
* Stable JSON serialisation for generating deterministic cache keys from
* structured arguments. Keys are sorted so the same data always produces
* the same string regardless of property insertion order.
*/
function stableJson(value: unknown): string {
if (value === null) return 'null';
if (typeof value !== 'object') return JSON.stringify(value);
if (Array.isArray(value)) {
return `[${value.map(stableJson).join(',')}]`;
}
const keys = Object.keys(value as Record<string, unknown>).sort();
const pairs = keys.map((k) => `${JSON.stringify(k)}:${stableJson((value as Record<string, unknown>)[k])}`);
return `{${pairs.join(',')}}`;
}
/**
* Compute a deterministic SHA-256 fingerprint for a combined spec + args
* payload. Used by the resumability cache to detect unchanged agent tasks.
*
* Exported for testing.
*/
export function fingerprintAgentTask(
prompt: string,
spec: Record<string, unknown>,
args: string,
): string {
return createHash('sha256')
.update(stableJson({ prompt, spec, args }))
.digest('hex');
}
// ---------------------------------------------------------------------------
// Built-in workflow definitions
// ---------------------------------------------------------------------------
function generateDeepResearchScript(_args?: Record<string, unknown>): string {
return `
export const meta = {
name: 'deep-research',
description: 'Multi-phase deep research: scope, search, fetch, verify, synthesise.',
phases: [
{ title: 'Scope', detail: 'Define the research question and search criteria' },
{ title: 'Search', detail: 'Query web sources in parallel' },
{ title: 'Fetch', detail: 'Retrieve full content from top sources' },
{ title: 'Verify', detail: 'Cross-reference and validate findings' },
{ title: 'Synthesise', detail: 'Produce a final structured report' },
],
};
export default async function main(args) {
const query = args?.query ?? 'No query provided';
log('deep-research: starting with query: ' + query);
// Phase 1: Scope
phase('Scope');
const scope = await agent(
'Analyse this research query and produce a search plan with 3-5 key sub-questions: ' + query,
{ label: 'scope-analysis', phase: 'scope' },
);
log('Scope completed');
// Phase 2: Search
phase('Search');
const searchResults = await agent(
'Based on the scope, search for authoritative sources. Return a list of 3-5 URLs with brief annotations.',
{ label: 'web-search', phase: 'search' },
);
log('Search completed');
// Phase 3: Fetch
phase('Fetch');
const fetchedContent = await agent(
'Extract and summarise the key information from these sources: ' + JSON.stringify(searchResults),
{ label: 'content-fetch', phase: 'fetch' },
);
log('Fetch completed');
// Phase 4: Verify
phase('Verify');
const verified = await agent(
'Cross-reference the fetched information. Note any contradictions, gaps, or weak sources: ' + JSON.stringify(fetchedContent),
{ label: 'verification', phase: 'verify' },
);
log('Verify completed');
// Phase 5: Synthesise
phase('Synthesise');
const report = await agent(
'Synthesise the verified information into a structured report with findings, sources, and confidence levels: ' + JSON.stringify(verified),
{ label: 'synthesis', phase: 'synthesise' },
);
log('deep-research: completed');
return {
ok: true,
output: report,
phases: { scope, searchResults, fetchedContent, verified, report },
};
}
`.trim();
}
function generateReviewCodeScript(_args?: Record<string, unknown>): string {
return `
export const meta = {
name: 'review-code',
description: 'Multi-perspective code review: correctness, security, performance, then synthesise.',
phases: [
{ title: 'Correctness', detail: 'Check logic, edge cases, and correctness' },
{ title: 'Security', detail: 'Analyse for vulnerabilities and unsafe patterns' },
{ title: 'Performance', detail: 'Identify performance bottlenecks and optimisation opportunities' },
{ title: 'Synthesise', detail: 'Merge perspectives into a unified review report' },
],
};
export default async function main(args) {
const target = args?.target ?? args?.path ?? '';
log('review-code: starting review of: ' + (target || '(no target specified)'));
const context = await agent(
'Read the code at ' + (target || 'the provided context') + ' and produce a summary of its structure and purpose.',
{ label: 'read-context', phase: 'context' },
);
// Phase 1: Correctness
phase('Correctness');
const correctness = await agent(
'Review this code for correctness. Check logical errors, edge cases, type safety, and concurrency issues:\\n' + JSON.stringify(context),
{ label: 'correctness-review', phase: 'correctness' },
);
// Phase 2: Security
phase('Security');
const security = await agent(
'Review this code for security vulnerabilities. Check for injection, auth bypasses, unsafe deserialisation, secret exposure:\\n' + JSON.stringify(context),
{ label: 'security-review', phase: 'security' },
);
// Phase 3: Performance
phase('Performance');
const performance = await agent(
'Review this code for performance issues. Check algorithmic complexity, unnecessary allocations, I/O patterns, caching opportunities:\\n' + JSON.stringify(context),
{ label: 'performance-review', phase: 'performance' },
);
// Phase 4: Synthesise
phase('Synthesise');
const report = await agent(
'Merge these three review perspectives into one structured report with severity-ranked findings:\\n' +
'--- Correctness ---\\n' + JSON.stringify(correctness) + '\\n' +
'--- Security ---\\n' + JSON.stringify(security) + '\\n' +
'--- Performance ---\\n' + JSON.stringify(performance),
{ label: 'synthesis', phase: 'synthesise' },
);
log('review-code: completed');
return {
ok: true,
output: report,
reviews: { correctness, security, performance },
};
}
`.trim();
}
function generateFindIssuesScript(_args?: Record<string, unknown>): string {
return `
export const meta = {
name: 'find-issues',
description: 'Iterative issue discovery — keep surfacing issues until consecutive rounds find nothing new.',
phases: [
{ title: 'Analyse', detail: 'Analyse the codebase for issues' },
{ title: 'Check dry', detail: 'Verify no new issues remain' },
],
};
export default async function main(args) {
const target = args?.target ?? args?.path ?? '.';
const maxRounds = args?.maxRounds ?? 5;
log('find-issues: starting on ' + target + ' (max ' + maxRounds + ' rounds)');
const allIssues = [];
let dryRounds = 0;
let round = 0;
while (dryRounds < 2 && round < maxRounds) {
round++;
phase('Analyse');
const context = allIssues.length > 0
? 'Previously found issues (exclude these):\\n' + JSON.stringify(allIssues)
: 'No issues found yet.';
const newIssues = await agent(
'Analyse ' + target + ' for bugs, code smells, and anti-patterns.\\n' + context + '\\nReturn a JSON array of issues. If none found, return an empty array.',
{ label: 'round-' + round + '-analysis', phase: 'analyse' },
);
let parsed: unknown[] = [];
try {
if (typeof newIssues === 'string') {
parsed = JSON.parse(newIssues);
} else if (Array.isArray(newIssues)) {
parsed = newIssues;
}
} catch {
parsed = [];
}
if (parsed.length === 0) {
dryRounds++;
phase('Check dry');
log('Round ' + round + ': no new issues found (dry run ' + dryRounds + '/2)');
} else {
dryRounds = 0;
for (const issue of parsed) {
allIssues.push(issue);
}
log('Round ' + round + ': found ' + parsed.length + ' new issue(s)');
}
}
log('find-issues: completed after ' + round + ' rounds, ' + allIssues.length + ' total issues');
return {
ok: true,
output: allIssues,
totalRounds: round,
totalIssues: allIssues.length,
};
}
`.trim();
}
// ---------------------------------------------------------------------------
// Registry
// ---------------------------------------------------------------------------
/**
* All built-in workflow definitions shipped with BooCode.
*/
const BUILTIN_WORKFLOWS: BuiltinWorkflow[] = [
{
name: 'deep-research',
description:
'Performs multi-phase deep research: scope the question, search web sources in parallel, fetch full content, verify findings, and synthesise a structured report.',
phases: [
{ title: 'Scope', detail: 'Define the research question and search criteria' },
{ title: 'Search', detail: 'Query web sources in parallel' },
{ title: 'Fetch', detail: 'Retrieve full content from top sources' },
{ title: 'Verify', detail: 'Cross-reference and validate findings' },
{ title: 'Synthesise', detail: 'Produce a final structured report' },
],
generateScript: generateDeepResearchScript,
},
{
name: 'review-code',
description:
'Multi-perspective code review that analyses code for correctness, security vulnerabilities, and performance issues in parallel, then merges findings into a unified severity-ranked report.',
phases: [
{ title: 'Correctness', detail: 'Check logic, edge cases, and correctness' },
{ title: 'Security', detail: 'Analyse for vulnerabilities and unsafe patterns' },
{ title: 'Performance', detail: 'Identify performance bottlenecks' },
{ title: 'Synthesise', detail: 'Merge perspectives into a unified report' },
],
generateScript: generateReviewCodeScript,
},
{
name: 'find-issues',
description:
'Iterative issue discovery that runs analysis rounds until two consecutive passes find nothing new, ensuring comprehensive coverage without infinite loops.',
phases: [
{ title: 'Analyse', detail: 'Analyse the codebase for issues' },
{ title: 'Check dry', detail: 'Verify no new issues remain' },
],
generateScript: generateFindIssuesScript,
},
];
/**
* Read-only map of built-in workflows keyed by name.
*/
const BUILTIN_WORKFLOW_MAP = new Map<string, BuiltinWorkflow>(
BUILTIN_WORKFLOWS.map((w) => [w.name, w]),
);
/**
* Return all built-in workflow definitions.
*/
export function getBuiltinWorkflows(): BuiltinWorkflow[] {
return BUILTIN_WORKFLOWS;
}
/**
* Look up a built-in workflow by name.
*
* @param name - Workflow name (e.g. 'deep-research').
* @returns The built-in workflow, or undefined if not found.
*/
export function getBuiltinWorkflow(name: string): BuiltinWorkflow | undefined {
return BUILTIN_WORKFLOW_MAP.get(name);
}
/**
* Merge built-in workflow metadata into a list of file-discovered workflow
* entries. Built-in entries take precedence — if a user has a file-based
* workflow with the same name, the built-in version wins.
*
* @param fileWorkflows - Workflow metadata discovered from the filesystem.
* @returns Merged array with built-in workflows injected and duplicate names
* resolved (built-in wins).
*/
export function mergeBuiltinWorkflows(
fileWorkflows: Array<{ name: string; description: string; sourceFile?: string }>,
): Array<{ name: string; description: string; sourceFile?: string }> {
const seen = new Set<string>();
const result: Array<{ name: string; description: string; sourceFile?: string }> = [];
// Built-in workflows first (they take precedence)
for (const builtin of BUILTIN_WORKFLOWS) {
seen.add(builtin.name);
result.push({
name: builtin.name,
description: builtin.description,
// No sourceFile — built-in workflows are generated, not read from disk
});
}
// File-discovered workflows — skip any name already claimed by built-in
for (const fw of fileWorkflows) {
if (seen.has(fw.name)) continue;
seen.add(fw.name);
result.push(fw);
}
return result;
}

View File

@@ -0,0 +1,134 @@
// v2.8.0: Workflow file discovery — walks project-local and global workflow
// directories to find runnable scripts. Built-in workflows from the catalog
// are merged into the results (they take precedence over user-defined files).
// All functions exported for testing.
import { readdirSync, existsSync } from 'node:fs';
import { join, basename, extname } from 'node:path';
import { homedir } from 'node:os';
import { getBuiltinWorkflows, getBuiltinWorkflow } from './catalog.js';
/**
* Sentinel prefix used in `sourceFile` for built-in workflows from the
* catalog so callers (e.g. WorkflowManager) can detect and handle them
* by calling `generateScript()` instead of reading a file from disk.
*/
const BUILTIN_PREFIX = 'builtin:';
/**
* Metadata about a discovered workflow file (or built-in workflow).
*/
export interface WorkflowMeta {
/** Workflow name (file stem without .js extension). */
name: string;
/** Description loaded from the workflow module's `meta.description`.
* Empty string until loadWorkflowMeta() resolves it. */
description: string;
/** Absolute path to the .js file.
* For built-in workflows this is `'builtin:<name>'` — the caller
* should use `getBuiltinWorkflow(name)` and `generateScript()`
* instead of reading this path from disk. */
sourceFile: string;
}
/**
* Test whether a `WorkflowMeta.sourceFile` points to a built-in workflow
* (rather than a file on disk).
*
* @param meta - The workflow metadata to check.
*/
export function isBuiltinWorkflow(meta: WorkflowMeta): boolean {
return meta.sourceFile.startsWith(BUILTIN_PREFIX);
}
/**
* Find all workflow .js files in the standard search paths, merged with
* built-in workflows from the catalog.
*
* Priority order (first match wins for same-named workflows):
* 1. Built-in catalog (always takes precedence)
* 2. <projectRoot>/.boocode/workflows/ (project-local)
* 3. ~/.boocode/workflows/ (global, per-user)
*
* @param projectRoot - Absolute path to the current project root.
*/
export function discoverWorkflows(projectRoot: string): WorkflowMeta[] {
const seen = new Set<string>();
const results: WorkflowMeta[] = [];
// 1. Built-in workflows (highest priority)
for (const builtin of getBuiltinWorkflows()) {
seen.add(builtin.name);
results.push({
name: builtin.name,
description: builtin.description,
sourceFile: `${BUILTIN_PREFIX}${builtin.name}`,
});
}
// 2. Project-local + global file-based workflows
const dirs = [
join(projectRoot, '.boocode', 'workflows'),
join(homedir(), '.boocode', 'workflows'),
];
for (const dir of dirs) {
if (!existsSync(dir)) continue;
try {
const entries = readdirSync(dir);
for (const f of entries) {
if (!f.endsWith('.js')) continue;
const name = basename(f, '.js');
if (seen.has(name)) continue; // built-in shadows project-local,
// project-local shadows global
seen.add(name);
results.push({
name,
description: '',
sourceFile: join(dir, f),
});
}
} catch {
// Permission error on directory — skip silently
continue;
}
}
return results;
}
/**
* Find a single workflow by name across built-in catalog and search paths.
*
* Priority: built-in > project-local > global.
*
* @param name - Workflow name (without .js extension).
* @param projectRoot - Absolute path to the current project root.
*/
export function findWorkflow(
name: string,
projectRoot: string,
): WorkflowMeta | undefined {
// Check built-in catalog first
const builtin = getBuiltinWorkflow(name);
if (builtin) {
return {
name: builtin.name,
description: builtin.description,
sourceFile: `${BUILTIN_PREFIX}${builtin.name}`,
};
}
// Fall back to file-based discovery
return discoverWorkflows(projectRoot).find((w) => w.name === name);
}
/**
* Validate a candidate workflow file path.
* Checks that the file exists and has a .js extension.
*
* @param filePath - Absolute path to check.
*/
export function isValidWorkflowPath(filePath: string): boolean {
return extname(filePath) === '.js' && existsSync(filePath);
}

View File

@@ -0,0 +1,54 @@
// v2.8.0: Dynamic Workflow Engine — public surface.
//
// Re-exports all types and classes from the workflow sub-modules so consumers
// import from a single entry point:
//
// ```typescript
// import { WorkflowManager } from './services/workflow/index.js';
// ```
export { WorkflowManager } from './manager.js';
export type { WorkflowMetaInfo } from './manager.js';
export type { WorkflowEventHandler } from './manager.js';
export { discoverWorkflows, findWorkflow, isValidWorkflowPath, isBuiltinWorkflow } from './discovery.js';
export type { WorkflowMeta } from './discovery.js';
export {
loadWorkflowScript,
loadWorkflowScriptFromCode,
executeWorkflowScript,
executeWorkflowScriptFromCode,
buildSandbox,
transformEsmToCjs,
isEsmSyntax,
} from './sandbox.js';
export {
getBuiltinWorkflows,
getBuiltinWorkflow,
mergeBuiltinWorkflows,
fingerprintAgentTask,
} from './catalog.js';
export type { BuiltinWorkflow } from './catalog.js';
export {
cacheKey,
getCachedResult,
setCachedResult,
invalidateRun,
clearCache,
cacheSize,
} from './resumability.js';
export type { CachedResult } from './resumability.js';
export type {
WorkflowScript,
WorkflowScriptMeta,
WorkflowContext,
AgentTaskSpec,
AgentTaskResult,
WorkflowRun,
WorkflowRunStatus,
WorkflowEvent,
} from './types.js';

View File

@@ -0,0 +1,659 @@
// v2.8.0: WorkflowManager — ties discovery, sandbox, and inference dispatch
// together into a single orchestrator for multi-agent workflow scripts.
//
// Creates isolated sessions+chats for each agent() call within a workflow,
// dispatches inference via the existing pipeline, polls for completion, and
// returns structured results. All failures are returned as errors rather than
// thrown exceptions (catch-safe API).
import { randomUUID } from 'node:crypto';
import type { Sql } from '../../db.js';
import type { Config } from '../../config.js';
import type { FastifyBaseLogger } from 'fastify';
import type { Broker } from '../broker.js';
import type { UserStreamFrame } from '../../types/api.js';
import type {
WorkflowRun,
WorkflowRunStatus,
WorkflowContext,
WorkflowEvent,
AgentTaskSpec,
AgentTaskResult,
WorkflowScriptMeta,
} from './types.js';
import { discoverWorkflows, findWorkflow, isBuiltinWorkflow } from './discovery.js';
import { getBuiltinWorkflow } from './catalog.js';
import { cacheKey, getCachedResult, setCachedResult } from './resumability.js';
import {
executeWorkflowScript,
executeWorkflowScriptFromCode,
isEsmSyntax,
transformEsmToCjs,
} from './sandbox.js';
import { runInference } from '../inference/index.js';
import { readFileSync } from 'node:fs';
import vm from 'node:vm';
/**
* Maximum time to wait for a single agent task to complete (5 minutes).
* Beyond this, the task is treated as failed/timed out.
*/
const AGENT_TASK_TIMEOUT_MS = 300_000;
/**
* Polling interval when waiting for an agent task to finish.
*/
const POLL_INTERVAL_MS = 500;
/**
* Maximum time for the entire workflow run (30 minutes).
*/
const WORKFLOW_TIMEOUT_MS = 1_800_000;
/**
* Token budget tracker. Tracks total token spend across agent calls.
*/
class BudgetTracker {
total: number | null;
#spent = 0;
constructor(total: number | null) {
this.total = total;
}
spend(amount: number): void {
this.#spent += amount;
}
spent(): number {
return this.#spent;
}
remaining(): number {
if (this.total === null) return Infinity;
return Math.max(0, this.total - this.#spent);
}
}
/**
* Creates a no-op bounded publish function that avoids WS dependency
* for background workflow agent tasks. Messages are still persisted to DB.
*/
function noopPublish(): void {
/* intentional no-op */
}
function noopPublishUser(): void {
/* intentional no-op */
}
/**
* Callback type for workflow lifecycle events.
*/
export type WorkflowEventHandler = (event: WorkflowEvent) => void;
/**
* WorkflowManager — the orchestrator for sandboxed multi-agent workflows.
*/
export class WorkflowManager {
/** Active workflow runs by run ID. */
readonly #runs = new Map<string, WorkflowRunState>();
/** Registered event listeners. */
readonly #listeners = new Set<WorkflowEventHandler>();
constructor(
private sql: Sql,
private config: Config,
private log: FastifyBaseLogger,
private projectRoot: string,
private projectId: string,
private broker: Broker,
) {}
// ---- public API ----
/**
* Discover all available workflow scripts.
*/
listWorkflows(): WorkflowMetaInfo[] {
return discoverWorkflows(this.projectRoot).map((m) => ({
name: m.name,
sourceFile: m.sourceFile,
}));
}
/**
* Find a specific workflow by name.
*/
getWorkflow(name: string): WorkflowMetaInfo | undefined {
const found = findWorkflow(name, this.projectRoot);
if (!found) return undefined;
return { name: found.name, sourceFile: found.sourceFile };
}
/**
* Load the metadata (name, description, phases) from a workflow file
* without executing it.
*
* @param name - Workflow name.
* @returns The script's meta, or undefined if not found.
*/
async loadWorkflowMeta(name: string): Promise<WorkflowScriptMeta | undefined> {
const found = findWorkflow(name, this.projectRoot);
if (!found) return undefined;
// Built-in workflows: return meta directly from the catalog
if (isBuiltinWorkflow(found)) {
const builtin = getBuiltinWorkflow(name);
if (!builtin) return { name, description: '' };
return {
name: builtin.name,
description: builtin.description,
phases: builtin.phases,
};
}
try {
// Load meta by executing the script in a throwaway context
const context = this.#createMinimalContext('meta-loader');
const code = readFileSync(found.sourceFile, 'utf8');
const finalCode = isEsmSyntax(code) ? transformEsmToCjs(code) : code;
const sandboxData: Record<string, unknown> & {
module: { exports: Record<string, unknown> };
} = {
...context,
console: { log: () => {} },
module: { exports: {} },
exports: {},
};
vm.createContext(sandboxData as unknown as vm.Context);
new vm.Script(finalCode).runInContext(sandboxData as unknown as vm.Context, {
timeout: 10_000,
filename: found.sourceFile,
});
const meta = sandboxData.module.exports.meta as WorkflowScriptMeta | undefined;
return meta ?? { name, description: '' };
} catch {
return { name, description: '' };
}
}
/**
* Execute a workflow by name.
*
* @param name - The workflow name (without .js extension).
* @param args - Optional arguments to pass to the workflow function.
* @returns The run ID for tracking.
*/
async runWorkflow(
name: string,
args?: Record<string, unknown>,
): Promise<{ runId: string }> {
const found = findWorkflow(name, this.projectRoot);
if (!found) {
throw new Error(`Workflow not found: "${name}". ` +
`Check .boocode/workflows/ or ~/.boocode/workflows/ for a ${name}.js file.`);
}
const runId = randomUUID();
const startedAt = new Date().toISOString();
const state: WorkflowRunState = {
id: runId,
name,
status: 'running',
startedAt,
abortController: new AbortController(),
};
this.#runs.set(runId, state);
this.#emit({ type: 'run_started', runId, name });
// Run asynchronously — caller receives the runId immediately.
void this.#executeRun(state, found.sourceFile, args ?? {});
return { runId };
}
/**
* Get the current status of a workflow run.
*/
getRunStatus(runId: string): WorkflowRun | undefined {
const state = this.#runs.get(runId);
if (!state) return undefined;
return {
id: state.id,
name: state.name,
status: state.status,
started_at: state.startedAt,
finished_at: state.finishedAt,
error: state.error,
};
}
/**
* Cancel a running workflow. Best-effort — agent tasks in-flight will be
* aborted via AbortSignal.
*
* @param runId - The workflow run ID.
* @returns true if the workflow was found and cancelled.
*/
cancelRun(runId: string): boolean {
const state = this.#runs.get(runId);
if (!state || state.status !== 'running') return false;
state.status = 'cancelled';
state.finishedAt = new Date().toISOString();
state.abortController.abort();
this.#emit({ type: 'run_cancelled', runId, name: state.name });
return true;
}
/**
* Subscribe to workflow lifecycle events.
* Returns an unsubscribe function.
*/
onEvent(handler: WorkflowEventHandler): () => void {
this.#listeners.add(handler);
return () => {
this.#listeners.delete(handler);
};
}
// ---- internal execution ----
/**
* Execute the workflow script in the sandbox.
*/
async #executeRun(
state: WorkflowRunState,
sourceFile: string,
args: Record<string, unknown>,
): Promise<void> {
const BULTIN_MARKER = 'builtin:';
const budgetTracker = new BudgetTracker(null); // no fixed total yet
const runId = state.id;
try {
const context: WorkflowContext = {
agent: (prompt, opts) =>
this.#handleAgentCall(runId, prompt, opts ?? { prompt }, state.abortController.signal),
parallel: (thunks) =>
Promise.all(thunks.map((t) => t())),
pipeline: async (items, ...stages) => {
let result = [...items];
for (const stage of stages) {
result = await Promise.all(result.map(stage));
}
return result;
},
phase: (title) => {
this.#emit({ type: 'phase', runId, title });
},
log: (message) => {
this.#emit({ type: 'log', runId, message });
},
budget: {
total: budgetTracker.total,
spent: () => budgetTracker.spent(),
remaining: () => budgetTracker.remaining(),
},
args,
workflow: (nestedName, nestedArgs) =>
this.#handleNestedWorkflow(runId, nestedName, nestedArgs ?? {}, state.abortController.signal),
};
let result: unknown;
if (sourceFile.startsWith(BULTIN_MARKER)) {
// Built-in workflow: generate script from catalog and execute
const workflowName = sourceFile.slice(BULTIN_MARKER.length);
const builtin = getBuiltinWorkflow(workflowName);
if (!builtin) {
throw new Error(`Built-in workflow "${workflowName}" not found in catalog`);
}
const scriptCode = builtin.generateScript(args);
result = await executeWorkflowScriptFromCode(scriptCode, context, args, sourceFile);
} else {
result = await executeWorkflowScript(sourceFile, context, args);
}
// Only update to completed if we haven't been cancelled mid-flight.
if (state.status !== 'cancelled') {
state.status = 'completed';
state.finishedAt = new Date().toISOString();
}
// Store result
state.result = result;
this.#emit({ type: 'run_completed', runId, name: state.name });
} catch (err) {
if (state.status === 'cancelled') return; // already handled
const message = err instanceof Error ? err.message : String(err);
state.status = 'failed';
state.finishedAt = new Date().toISOString();
state.error = message;
this.#emit({ type: 'run_failed', runId, name: state.name, error: message });
}
}
/**
* Handle an `agent()` call from within a workflow.
* Creates a session + chat, dispatches inference, polls for completion.
*/
async #handleAgentCall(
runId: string,
prompt: string,
spec: AgentTaskSpec,
signal: AbortSignal,
): Promise<unknown> {
const label = spec.label ?? `agent-${prompt.slice(0, 40).replace(/\s+/g, '_')}`;
this.#emit({ type: 'agent_task_started', runId, label });
try {
const result = await this.executeAgentTask(prompt, spec, signal);
this.#emit({ type: 'agent_task_completed', runId, label });
return result;
} catch (err) {
this.#emit({ type: 'agent_task_completed', runId, label });
const message = err instanceof Error ? err.message : String(err);
return {
ok: false,
output: null,
error: message,
} satisfies AgentTaskResult;
}
}
/**
* Core agent task execution: create session/chat, dispatch inference, poll.
*
* Exported as a public method for testing.
*/
async executeAgentTask(
prompt: string,
spec: AgentTaskSpec,
signal?: AbortSignal,
): Promise<unknown> {
// ---- 0. Check resumability cache before creating a new task ----
const cacheKeyStr = cacheKey(spec, '');
const cached = getCachedResult(cacheKeyStr);
if (cached) {
return { ...cached, cached: true } satisfies AgentTaskResult;
}
const model = spec.model ?? null;
// ---- 1. Create a session for this agent task ----
const sessionName = `workflow-agent-${spec.label ?? 'task'}`;
const sessionResult = await this.sql.begin(async (tx) => {
const [session] = await tx<{ id: string }[]>`
INSERT INTO sessions (project_id, name, model)
VALUES (${this.projectId}, ${sessionName}, ${model ?? 'qwen3.6-35b-a3b-mxfp4'})
RETURNING id
`;
if (!session) throw new Error('Failed to create workflow agent session');
return session;
});
const sessionId = sessionResult.id;
// ---- 2. Create a chat in this session ----
const chatResult = await this.sql.begin(async (tx) => {
const [chat] = await tx<{ id: string }[]>`
INSERT INTO chats (session_id, name)
VALUES (${sessionId}, ${spec.label ?? null})
RETURNING id
`;
if (!chat) throw new Error('Failed to create workflow agent chat');
return chat;
});
const chatId = chatResult.id;
// ---- 3. Insert user message + streaming assistant message ----
const { userMessageId, assistantMessageId } = await this.sql.begin(async (tx) => {
const [userMsg] = await tx<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'user', ${prompt}, 'complete', clock_timestamp())
RETURNING id
`;
const [assistantMsg] = await tx<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
RETURNING id
`;
return {
userMessageId: userMsg!.id,
assistantMessageId: assistantMsg!.id,
};
});
// ---- 4. Dispatch inference ----
// Create a bounded InferenceContext that won't crash on missing WS
const ctx: import('../inference/types.js').InferenceContext = {
sql: this.sql,
config: this.config,
log: this.log,
publish: noopPublish as unknown as import('../inference/types.js').FramePublisher,
publishUser: noopPublishUser as unknown as (frame: UserStreamFrame) => void,
broker: this.broker,
};
// Create a merged signal (workflow cancellation + optional caller signal)
const mergedController = new AbortController();
const onAbort = () => mergedController.abort();
signal?.addEventListener('abort', onAbort, { once: true });
const inferencePromise = runInference(
ctx,
sessionId,
chatId,
assistantMessageId,
mergedController.signal,
).finally(() => {
signal?.removeEventListener('abort', onAbort);
});
// ---- 5. Poll for completion ----
try {
const result = await this.#pollForCompletion(
chatId,
assistantMessageId,
inferencePromise,
mergedController.signal,
);
// Cache successful results for resumability
if (typeof result === 'object' && result !== null && (result as Record<string, unknown>).ok === true) {
setCachedResult(cacheKeyStr, {
ok: true,
output: (result as Record<string, unknown>).output,
token_usage: (result as Record<string, unknown>).token_usage as
| { prompt: number; completion: number }
| undefined,
});
}
return result;
} catch (err) {
if ((err as Error)?.message === 'cancelled') {
return { ok: false, output: null, error: 'Task was cancelled' } satisfies AgentTaskResult;
}
return {
ok: false,
output: null,
error: err instanceof Error ? err.message : String(err),
} satisfies AgentTaskResult;
}
}
/**
* Poll the messages table until the assistant message status changes
* from 'streaming' to 'complete' / 'failed' / 'cancelled'.
*/
async #pollForCompletion(
chatId: string,
assistantMessageId: string,
inferencePromise: Promise<void>,
signal: AbortSignal,
): Promise<unknown> {
// Wait for either inference to finish or timeout
const timeout = new Promise<never>((_, reject) => {
const timer = setTimeout(() => {
reject(new Error(`Agent task timed out after ${AGENT_TASK_TIMEOUT_MS}ms`));
}, AGENT_TASK_TIMEOUT_MS);
signal.addEventListener('abort', () => {
clearTimeout(timer);
reject(new Error('cancelled'));
}, { once: true });
});
// Poll loop — runs until inference completes, timeout, or cancellation
const pollLoop = (async () => {
// eslint-disable-next-line no-constant-condition
while (true) {
await new Promise((resolve) => setTimeout(resolve, POLL_INTERVAL_MS));
const rows = await this.sql<{
status: string;
content: string;
tool_calls: unknown;
tokens_used: number | null;
}[]>`
SELECT m.status, m.content, m.role,
(SELECT jsonb_agg(p.payload ORDER BY p.sequence)
FROM message_parts p
WHERE p.message_id = m.id AND p.kind = 'tool_call' AND p.hidden_at IS NULL) AS tool_calls,
m.tokens_used
FROM messages m
WHERE m.id = ${assistantMessageId}
`;
const msg = rows[0];
if (!msg) {
throw new Error(`Assistant message ${assistantMessageId} not found`);
}
if (msg.status === 'complete') {
return {
ok: true,
output: msg.content,
token_usage: msg.tokens_used ? { prompt: 0, completion: msg.tokens_used } : undefined,
};
}
if (msg.status === 'failed' || msg.status === 'cancelled') {
return {
ok: false,
output: msg.content || null,
error: `Assistant message ended with status: ${msg.status}`,
};
}
// Still streaming — continue polling
}
})();
// Race: polling vs timeout vs inference error vs cancellation
try {
return await Promise.race([pollLoop, timeout]);
} finally {
// Ensure inference is settled (but don't block on it)
inferencePromise.catch(() => {});
}
}
/**
* Handle a nested `workflow()` call from within a workflow.
* Runs the named workflow with the given args and returns its result.
*/
async #handleNestedWorkflow(
parentRunId: string,
name: string,
args: Record<string, unknown>,
signal: AbortSignal,
): Promise<unknown> {
const found = findWorkflow(name, this.projectRoot);
if (!found) {
return { ok: false, output: null, error: `Nested workflow not found: "${name}"` };
}
const nestedRunId = randomUUID();
const startedAt = new Date().toISOString();
const nestedState: WorkflowRunState = {
id: nestedRunId,
name,
status: 'running',
startedAt,
abortController: new AbortController(),
};
this.#runs.set(nestedRunId, nestedState);
this.#emit({ type: 'run_started', runId: nestedRunId, name });
// Link parent cancellation to nested
signal.addEventListener('abort', () => {
nestedState.abortController.abort();
}, { once: true });
await this.#executeRun(nestedState, found.sourceFile, args);
if (nestedState.status === 'cancelled') {
return { ok: false, output: null, error: 'Nested workflow cancelled' };
}
if (nestedState.status === 'failed') {
return { ok: false, output: null, error: nestedState.error };
}
return { ok: true, output: nestedState.result };
}
/**
* Create a minimal WorkflowContext for non-execution purposes
* (e.g. loading meta).
*/
#createMinimalContext(runId: string): Record<string, unknown> {
return {
agent: () => Promise.reject(new Error('Not available in this context')),
parallel: () => Promise.reject(new Error('Not available in this context')),
pipeline: () => Promise.reject(new Error('Not available in this context')),
phase: () => {},
log: () => {},
budget: { total: null, spent: () => 0, remaining: () => Infinity },
args: {},
workflow: () => Promise.reject(new Error('Not available in this context')),
};
}
/**
* Emit a workflow event to all registered listeners.
*/
#emit(event: WorkflowEvent): void {
for (const handler of this.#listeners) {
try {
handler(event);
} catch {
// Swallow listener errors — one bad listener shouldn't break others
}
}
}
}
// ---- internal types ----
/**
* Metadata returned from listWorkflows / getWorkflow.
*/
export interface WorkflowMetaInfo {
name: string;
sourceFile: string;
}
/**
* Internal mutable state for an active workflow run.
*/
interface WorkflowRunState {
id: string;
name: string;
status: WorkflowRunStatus;
startedAt: string;
finishedAt?: string;
error?: string;
result?: unknown;
abortController: AbortController;
}

View File

@@ -0,0 +1,195 @@
// v2.8.0: Workflow resumability cache — SHA-256 hash-based in-memory cache
// for completed agent task results. When a workflow re-runs, completed agents
// with unchanged specs skip execution and return cached results.
//
// The cache is purely in-memory (Map). No DB persistence for v1.
// All functions are exported for testing.
import { createHash } from 'node:crypto';
import type { AgentTaskSpec } from './types.js';
// ---------------------------------------------------------------------------
// Types
// ---------------------------------------------------------------------------
/**
* Shape of a cached agent task result. Mirrors the successful fields of
* `AgentTaskResult` without the runtime-only `cached` flag.
*/
export interface CachedResult {
ok: boolean;
output: unknown;
error?: string;
token_usage?: { prompt: number; completion: number };
}
/**
* Internal cache entry with insertion timestamp for TTL support.
*/
interface CacheEntry {
result: CachedResult;
insertedAt: number;
}
// ---------------------------------------------------------------------------
// Cache store
// ---------------------------------------------------------------------------
/**
* Default TTL for cached entries (30 minutes).
* After this period entries are considered stale and are evicted on access.
*/
const DEFAULT_TTL_MS = 1_800_000;
/**
* Maximum number of entries before the cache starts evicting oldest entries.
*/
const MAX_ENTRIES = 500;
/**
* In-memory cache store: SHA-256 hash → cached result.
*/
const cache = new Map<string, CacheEntry>();
// ---------------------------------------------------------------------------
// Public API
// ---------------------------------------------------------------------------
/**
* Build a deterministic SHA-256 hash for an agent task specification.
*
* The hash is computed from a stable-ordered JSON serialisation of the spec
* (prompt + options) so that identical specs always produce the same key
* regardless of JavaScript property insertion order.
*
* @param spec - The agent task specification (prompt, options, etc.).
* @param args - Additional arguments string (e.g. workflow args fingerprint).
* @returns A 64-character hex SHA-256 digest.
*/
export function cacheKey(spec: AgentTaskSpec, args: string): string {
const hash = createHash('sha256');
// Stable-sorted serialisation of the spec
hash.update(stableJson(spec));
// Append the args fingerprint
hash.update('\0');
hash.update(args);
return hash.digest('hex');
}
/**
* Look up a cached result by its cache key.
*
* Returns `null` when:
* - The key doesn't exist in the cache.
* - The cached entry has exceeded the TTL (evicted silently).
*
* @param key - The SHA-256 hex key returned by `cacheKey()`.
* @returns The cached result, or `null` if not found or expired.
*/
export function getCachedResult(key: string): CachedResult | null {
const entry = cache.get(key);
if (!entry) return null;
// TTL check — stale entries are evicted on access
if (Date.now() - entry.insertedAt > DEFAULT_TTL_MS) {
cache.delete(key);
return null;
}
return entry.result;
}
/**
* Store an agent task result in the cache.
*
* If the cache has reached `MAX_ENTRIES`, the oldest entry (by insertion time)
* is evicted first. This is a simple FIFO eviction — not a full LRU — because
* workflow runs are expected to exhibit high temporal locality (recently
* completed steps in the current run are the most likely to be re-queried).
*
* @param key - The SHA-256 hex key returned by `cacheKey()`.
* @param result - The result to cache.
*/
export function setCachedResult(key: string, result: CachedResult): void {
// Evict oldest entry if at capacity
if (cache.size >= MAX_ENTRIES) {
let oldestKey: string | undefined;
let oldestTime = Infinity;
for (const [k, entry] of cache) {
if (entry.insertedAt < oldestTime) {
oldestTime = entry.insertedAt;
oldestKey = k;
}
}
if (oldestKey) {
cache.delete(oldestKey);
}
}
cache.set(key, {
result,
insertedAt: Date.now(),
});
}
/**
* Invalidate all cached entries that were produced during a specific workflow
* run. The `runKey` is matched as a prefix of the cache key — this works
* because `cacheKey()` incorporates the args string, and the caller passes
* a run-specific token as the `args` parameter.
*
* @param runKey - The run-specific key prefix to invalidate.
*/
export function invalidateRun(runKey: string): void {
for (const key of cache.keys()) {
if (key.startsWith(runKey)) {
cache.delete(key);
}
}
}
/**
* Clear the entire cache. Used for testing and manual reset.
*/
export function clearCache(): void {
cache.clear();
}
/**
* Return the current number of entries in the cache.
* Useful for testing assertions.
*/
export function cacheSize(): number {
return cache.size;
}
// ---------------------------------------------------------------------------
// Internal helpers
// ---------------------------------------------------------------------------
/**
* Stable JSON serialisation that produces the same output string for the same
* data regardless of JavaScript object property insertion order.
*
* - Object keys are sorted lexicographically.
* - Arrays preserve their element order.
* - Primitives are serialised via `JSON.stringify`.
*/
function stableJson(value: unknown): string {
if (value === null) return 'null';
if (typeof value !== 'object') return JSON.stringify(value);
if (Array.isArray(value)) {
return `[${value.map(stableJson).join(',')}]`;
}
const keys = Object.keys(value as Record<string, unknown>).sort();
const pairs = keys.map(
(k) =>
`${JSON.stringify(k)}:${stableJson((value as Record<string, unknown>)[k])}`,
);
return `{${pairs.join(',')}}`;
}

View File

@@ -0,0 +1,284 @@
// v2.8.0: VM sandbox for executing workflow scripts in an isolated Node.js
// context with a restricted global scope. Uses Node's built-in `vm` module
// (zero additional dependencies).
//
// Workflow scripts can use either CommonJS (`module.exports`) or ESM syntax
// (`export const` / `export default`). ESM syntax is automatically transformed
// to CJS before execution via a lightweight regex transform.
import vm from 'node:vm';
import { readFileSync } from 'node:fs';
import type { WorkflowContext } from './types.js';
/**
* Shared timeout for all sandboxed script execution.
* Prevents runaway workflows from blocking the server indefinitely.
*/
const EXECUTION_TIMEOUT_MS = 30_000;
/**
* Regex-based ESM-to-CJS transform for workflow scripts.
*
* Handles:
* - `export const|let|var <name> = <value>;` → `<name> = <value>;`
* - `export default <expression>;` → `default = <expression>;`
* - `export default function <name>(...) {...}` → `default = function <name>(...) {...}`
* - `export { <name1>, <name2> }` → removed (inline assignment)
*
* @param code - Raw source code (ESM or CJS).
* @returns Code transformed to CJS assignments suitable for vm.Script.
*/
export function transformEsmToCjs(code: string): string {
// Remove `export ` prefix from declarations and `export default` assignments.
// Order matters: handle `export default function` before bare `export default`.
let transformed = code
// export default async function name(...) {...} → default = async function name(...) {...}
.replace(
/export\s+default\s+(async\s+)?function\s*\**\s*(\w+)?\s*\(/g,
(_, asyncKw, _name) => {
return `default = ${asyncKw ?? ''}function ${_name ?? ''}(`;
},
)
// export default class Name {...} → default = class Name {...}
.replace(/export\s+default\s+(class\s+\w+)/g, 'default = $1')
// export default <expression>; → default = <expression>;
.replace(/export\s+default\s+/g, 'default = ')
// export const|let|var name = value → name = value
.replace(
/export\s+(const|let|var)\s+(\w+)\s*=/g,
(_, _decl, name) => `${name} =`,
)
// export function name(...) {...} → (hoisted, keep as-is but remove export)
.replace(/^export\s+(function\s+\w+)/gm, '$1')
// export class Name {...} → keep but remove export
.replace(/^export\s+(class\s+\w+)/gm, '$1')
// export { a, b, c } → (remove line)
.replace(/^export\s+\{[^}]*\}\s*;?\s*$/gm, '')
// export { a, b as c } → (remove line)
.replace(/^export\s+\{[^}]*\s+as\s+\w+[^}]*\}\s*;?\s*$/gm, '');
return transformed;
}
/**
* Determine whether code uses ESM export syntax (export keyword at line start
* or after optional whitespace).
*/
export function isEsmSyntax(code: string): boolean {
return /^\s*export\s+(const|let|var|function|class|default|\{)/m.test(code);
}
/**
* Build a restricted sandbox object with the workflow runtime API.
*
* @param context - The WorkflowContext methods to expose to the script.
* @returns A plain object suitable for vm.createContext().
*/
export function buildSandbox(context: WorkflowContext): Record<string, unknown> {
return {
// --- Workflow API (from context) ---
agent: context.agent,
parallel: context.parallel,
pipeline: context.pipeline,
phase: context.phase,
log: context.log,
budget: context.budget,
args: context.args,
workflow: context.workflow,
// --- Safe built-ins ---
console: {
log: context.log,
warn: context.log,
error: context.log,
},
setTimeout,
clearTimeout,
setInterval: undefined, // intentionally disabled
clearInterval: undefined, // intentionally disabled
Promise,
JSON,
Math,
Date,
RegExp,
Error,
Array,
Object,
String,
Number,
Boolean,
Map,
Set,
WeakMap,
WeakSet,
parseInt,
parseFloat,
isNaN,
isFinite,
Symbol,
BigInt,
undefined,
null: null,
true: true,
false: false,
// --- CommonJS interop ---
module: { exports: {} },
exports: {},
require: undefined, // intentionally disabled
global: undefined, // prevent escape via `globalThis`
};
}
/**
* Execute a workflow script in the sandbox and return its default export
* (the main async function).
*
* @param sourceFile - Absolute path to the .js workflow file.
* @param context - The WorkflowContext to expose to the script.
* @returns The workflow's default export function.
* @throws {Error} If the script doesn't export a default async function,
* or if execution fails.
*/
export function loadWorkflowScript(
sourceFile: string,
context: WorkflowContext,
): (...args: unknown[]) => Promise<unknown> {
const code = readFileSync(sourceFile, 'utf8');
const finalCode = isEsmSyntax(code) ? transformEsmToCjs(code) : code;
const rawSandbox = buildSandbox(context);
const sandbox = rawSandbox as Record<string, unknown> & {
module: { exports: Record<string, unknown> };
};
vm.createContext(sandbox);
try {
const script = new vm.Script(finalCode);
script.runInContext(sandbox, {
timeout: EXECUTION_TIMEOUT_MS,
filename: sourceFile,
});
} catch (err) {
const msg = err instanceof Error ? err.message : String(err);
throw new Error(`Workflow script execution failed: ${msg}`);
}
// Check module.exports first (CJS), then sandbox.default (ESM transform)
const exported = sandbox.module.exports.default ?? sandbox.default;
// Also support `module.exports = async function(...)` (direct assignment)
const mainFn =
typeof sandbox.module.exports === 'function'
? sandbox.module.exports
: exported;
if (typeof mainFn !== 'function') {
const exportedKeys = Object.keys({
...sandbox.module.exports,
...(sandbox.default ? { default: true } : {}),
});
throw new Error(
`Workflow script must export a default async function. ` +
`Found exports: ${exportedKeys.join(', ') || '(none)'}. ` +
`Make sure your script has "export default async function main(args) {...}".`,
);
}
// eslint-disable-next-line @typescript-eslint/no-unsafe-return
return mainFn as (...args: unknown[]) => Promise<unknown>;
}
/**
* Load a workflow script from a source code string (rather than a file).
* Useful for built-in workflows from the catalog that don't have a
* corresponding .js file on disk.
*
* @param code - The JavaScript source code of the workflow.
* @param context - The WorkflowContext to expose.
* @param filename - Virtual filename for stack traces (e.g. 'builtin://deep-research').
* @returns The workflow's default export function.
* @throws {Error} If the script doesn't export a default async function.
*/
export function loadWorkflowScriptFromCode(
code: string,
context: WorkflowContext,
filename?: string,
): (...args: unknown[]) => Promise<unknown> {
const finalCode = isEsmSyntax(code) ? transformEsmToCjs(code) : code;
const rawSandbox = buildSandbox(context);
const sandbox = rawSandbox as Record<string, unknown> & {
module: { exports: Record<string, unknown> };
};
vm.createContext(sandbox);
try {
const script = new vm.Script(finalCode);
script.runInContext(sandbox, {
timeout: EXECUTION_TIMEOUT_MS,
filename: filename ?? 'workflow:<anonymous>',
});
} catch (err) {
const msg = err instanceof Error ? err.message : String(err);
throw new Error(`Workflow script execution failed: ${msg}`);
}
const exported = sandbox.module.exports.default ?? sandbox.default;
const mainFn =
typeof sandbox.module.exports === 'function'
? sandbox.module.exports
: exported;
if (typeof mainFn !== 'function') {
const exportedKeys = Object.keys({
...sandbox.module.exports,
...(sandbox.default ? { default: true } : {}),
});
throw new Error(
`Workflow script must export a default async function. ` +
`Found exports: ${exportedKeys.join(', ') || '(none)'}.`,
);
}
// eslint-disable-next-line @typescript-eslint/no-unsafe-return
return mainFn as (...args: unknown[]) => Promise<unknown>;
}
/**
* High-level convenience: load and execute a workflow script in a single call.
*
* @param sourceFile - Absolute path to the .js workflow file.
* @param context - The WorkflowContext to expose.
* @param args - Optional arguments passed to the workflow function.
* @returns The workflow's return value.
*/
export async function executeWorkflowScript(
sourceFile: string,
context: WorkflowContext,
args?: Record<string, unknown>,
): Promise<unknown> {
const mainFn = loadWorkflowScript(sourceFile, context);
return mainFn(args);
}
/**
* Execute a workflow from source code (string) rather than a file.
* Convenience wrapper around `loadWorkflowScriptFromCode`.
*
* @param code - The JavaScript source code of the workflow.
* @param context - The WorkflowContext to expose.
* @param args - Optional arguments passed to the workflow function.
* @param filename - Virtual filename for stack traces.
* @returns The workflow's return value.
*/
export async function executeWorkflowScriptFromCode(
code: string,
context: WorkflowContext,
args?: Record<string, unknown>,
filename?: string,
): Promise<unknown> {
const mainFn = loadWorkflowScriptFromCode(code, context, filename);
return mainFn(args);
}

View File

@@ -0,0 +1,128 @@
// v2.8.0: Dynamic Workflow Engine — types for the sandboxed multi-agent
// orchestration runtime. All types are exported for testing.
/**
* The expected shape of a workflow script module.
* Workflow files are plain .js files that export `meta` and `default`:
*
* ```js
* export const meta = {
* name: 'my-workflow',
* description: 'Does something useful in phases',
* phases: [
* { title: 'Research', detail: 'Gather context' },
* { title: 'Implement', detail: 'Make changes' },
* ],
* };
*
* export default async function main(args) {
* const result = await agent('...');
* return result;
* }
* ```
*/
export interface WorkflowScriptMeta {
name: string;
description: string;
phases?: Array<{ title: string; detail?: string }>;
}
export interface WorkflowScript {
meta: WorkflowScriptMeta;
default: (args?: Record<string, unknown>) => Promise<unknown>;
}
/**
* Specification for dispatching a single agent task within a workflow.
*/
export interface AgentTaskSpec {
/** The instruction prompt for the agent. */
prompt: string;
/** Optional human-readable label for this task (shown in UI). */
label?: string;
/** Phase identifier for grouping tasks. */
phase?: string;
/** Model override (defaults to session/chat model). */
model?: string;
/** Zod-style JSON schema for structured output validation. */
schema?: Record<string, unknown>;
/** Required capabilities the agent must have. */
capabilities?: string[];
/** Per-agent tool-call budget ceiling. */
max_tool_calls?: number;
/** Per-agent step cap for the inference loop. */
max_tool_iters?: number;
}
/**
* Result returned after an agent task completes.
*/
export interface AgentTaskResult {
ok: boolean;
output: unknown;
error?: string;
token_usage?: { prompt: number; completion: number };
/** True when this result was served from the resumability cache
* rather than re-executing the agent task. */
cached?: boolean;
}
/**
* Runtime context passed into every workflow script's default function.
* Mirrors the Claude Code-compatible API surface.
*/
export interface WorkflowContext {
/** Dispatch a single agent prompt. Returns the assistant's reply content. */
agent: (prompt: string, opts?: AgentTaskSpec) => Promise<unknown>;
/** Run multiple independent tasks concurrently. Returns results in order. */
parallel: (thunks: Array<() => Promise<unknown>>) => Promise<unknown[]>;
/** Pass items through a sequence of transform stages. */
pipeline: (
items: unknown[],
...stages: Array<(item: unknown) => Promise<unknown>>
) => Promise<unknown[]>;
/** Announce the current execution phase (for UI progress). */
phase: (title: string) => void;
/** Emit a log message for this workflow run. */
log: (message: string) => void;
/** Token budget tracker for the current run. */
budget: {
total: number | null;
spent: () => number;
remaining: () => number;
};
/** The arguments passed when this workflow was started. */
args: Record<string, unknown>;
/** Call another workflow from within a workflow (nested). */
workflow: (name: string, args?: Record<string, unknown>) => Promise<unknown>;
}
/**
* Status of a workflow execution run.
*/
export type WorkflowRunStatus = 'running' | 'completed' | 'failed' | 'cancelled';
/**
* Persistent record of a workflow run.
*/
export interface WorkflowRun {
id: string;
name: string;
status: WorkflowRunStatus;
started_at: string;
finished_at?: string;
error?: string;
}
/**
* Event emitted by the workflow manager for subscribers.
*/
export type WorkflowEvent =
| { type: 'run_started'; runId: string; name: string }
| { type: 'run_completed'; runId: string; name: string }
| { type: 'run_failed'; runId: string; name: string; error: string }
| { type: 'run_cancelled'; runId: string; name: string }
| { type: 'phase'; runId: string; title: string }
| { type: 'log'; runId: string; message: string }
| { type: 'agent_task_started'; runId: string; label?: string }
| { type: 'agent_task_completed'; runId: string; label?: string };