feat(conductor): Wave 2 — parallel batch execution + SWITCH branching step
- Parallel batch execution: batch field on Step, batchConfig on Flow, batch-aware readySteps with maxConcurrent gating, getReadyInBatch helper - SWITCH branching step: new 'switch' StepKind with cases/programmed conditions, resolveSwitch() pure function, switch-excluded steps tracked in SchedulerState, non-selected branches excluded from execution
This commit is contained in:
@@ -40,11 +40,14 @@ import { getFlow } from '../conductor/flows/index.js';
|
||||
import { loadPersona } from '../conductor/persona-loader.js';
|
||||
import type { Band, DispatchFn, Flow, FlowInput, Step, StepContext } from '../conductor/types.js';
|
||||
import {
|
||||
buildBatchState,
|
||||
getReadyInBatch,
|
||||
isRunComplete,
|
||||
manifestSteps,
|
||||
partitionReady,
|
||||
readySteps,
|
||||
reconcileRun,
|
||||
resolveSwitch,
|
||||
type SchedulerState,
|
||||
type StepResumeDecision,
|
||||
} from './flow-runner-decisions.js';
|
||||
@@ -95,7 +98,7 @@ interface Deps {
|
||||
|
||||
interface FlowStepRow {
|
||||
step_id: string;
|
||||
kind: 'agent' | 'code';
|
||||
kind: 'agent' | 'code' | 'switch';
|
||||
agent: string | null;
|
||||
status: string;
|
||||
chat_id: string | null;
|
||||
@@ -280,6 +283,8 @@ export function createFlowRunner(deps: Deps): FlowRunner {
|
||||
const skipped = new Set<string>();
|
||||
const inFlight = new Set<string>();
|
||||
const timedOut = new Set<string>();
|
||||
/** Per-switch routing results — maps switch step id → resolved branch details */
|
||||
const switchExcluded = new Map<string, { chosenCase: string | null; excluded: Set<string> }>();
|
||||
const results: Record<string, string> = {};
|
||||
for (const r of rows) {
|
||||
switch (r.status) {
|
||||
@@ -311,6 +316,8 @@ export function createFlowRunner(deps: Deps): FlowRunner {
|
||||
// ─── Timeout detection ───────────────────────────────────────────────────────
|
||||
// Check running steps. If a step has been 'running' longer than
|
||||
// FLOW_STEP_TIMEOUT_MS, mark it timed_out or re-dispatch if retriable.
|
||||
// Build a context here so the timeout retry path can re-dispatch the step.
|
||||
const timeoutCtx = buildCtx(input, results, model, dispatch);
|
||||
const timeoutMs = config.FLOW_STEP_TIMEOUT_MS;
|
||||
const nowDate = new Date();
|
||||
let detectedTimedOut = false;
|
||||
@@ -341,7 +348,7 @@ export function createFlowRunner(deps: Deps): FlowRunner {
|
||||
SET retry_count = ${retryCount + 1}, updated_at = clock_timestamp()
|
||||
WHERE run_id = ${runId} AND step_id = ${r.step_id} AND status = 'running'
|
||||
`;
|
||||
await dispatchAgentStep(runId, run.project_id, model, step, ctx);
|
||||
await dispatchAgentStep(runId, run.project_id, model, step, timeoutCtx);
|
||||
inFlight.add(r.step_id);
|
||||
log.warn({ runId, stepId: r.step_id, retry: retryCount + 1, maxRetries },
|
||||
'flow-runner: step timed out, retrying');
|
||||
@@ -369,14 +376,16 @@ export function createFlowRunner(deps: Deps): FlowRunner {
|
||||
// Drain ready skips + code steps (synchronous), re-evaluating after each batch,
|
||||
// then dispatch the full ready agent wave and wait for their terminal callbacks.
|
||||
for (;;) {
|
||||
const state: SchedulerState = { done, skipped, inFlight, excluded, timedOut };
|
||||
// Build per-batch state from the current inFlight set for batch parallelism gating.
|
||||
const batchState = buildBatchState(flow, inFlight);
|
||||
const state: SchedulerState = { done, skipped, inFlight, excluded, timedOut, batchState, switchResults: switchExcluded };
|
||||
|
||||
if (isRunComplete(flow, state)) {
|
||||
await finishRun(runId, flow, input, results, model, dispatch);
|
||||
return;
|
||||
}
|
||||
|
||||
const ready = readySteps(flow, state);
|
||||
const ready = getReadyInBatch(readySteps(flow, state), state, flow);
|
||||
if (ready.length === 0) {
|
||||
if (inFlight.size > 0) return; // agents in flight will re-enter via the hook
|
||||
await failRun(runId, flow, input, model, 'unsatisfiable dependencies / cycle');
|
||||
@@ -395,6 +404,31 @@ export function createFlowRunner(deps: Deps): FlowRunner {
|
||||
continue; // re-evaluate — a skip can settle a fan-in step's deps
|
||||
}
|
||||
|
||||
// SWITCH steps run synchronously — evaluate conditions, update the excluded
|
||||
// set in SchedulerState, and mark themselves complete. Non-selected branch
|
||||
// step ids are excluded from ever running.
|
||||
const switchReady = toRun.filter((s) => s.kind === 'switch');
|
||||
if (switchReady.length > 0) {
|
||||
for (const s of switchReady) {
|
||||
let result: { chosenCase: string | null; excluded: string[] };
|
||||
try {
|
||||
result = resolveSwitch(s, buildCtx(input, results, model, dispatch));
|
||||
} catch (err) {
|
||||
await failRun(runId, flow, input, model, `switch step '${s.id}' threw: ${errMsg(err)}`, s.id);
|
||||
return;
|
||||
}
|
||||
switchExcluded.set(s.id, {
|
||||
chosenCase: result.chosenCase,
|
||||
excluded: new Set(result.excluded),
|
||||
});
|
||||
const outputText = result.chosenCase ? `branch:${result.chosenCase}` : '';
|
||||
await markStep(runId, s.id, 'completed', outputText);
|
||||
results[s.id] = outputText;
|
||||
done.add(s.id);
|
||||
}
|
||||
continue; // re-evaluate — excluded steps may unblock dependents
|
||||
}
|
||||
|
||||
const codeReady = toRun.filter((s) => s.kind === 'code');
|
||||
if (codeReady.length > 0) {
|
||||
for (const s of codeReady) {
|
||||
|
||||
Reference in New Issue
Block a user