* feat: add Runpod serverless image collector pools * fix: prevent worker settings clipping and remove preview copy * fix: initialize worker settings before mounting the form * fix: validate complete serverless requests against 10 MB limit * fix: simplify serverless cards and keep status dots circular * fix: match serverless endpoint box to master card * fix: preserve serverless capacity and recovery across job failures Retain durable reservations until provider termination or explicit recovery, protect unresolved pools and credentials, and add scoped reconciliation. Consolidate lifecycle and secret policies and split prompt/media stages with regression coverage. * feat: add dynamic per-image list queue with Start and End nodes * fix(image-list): reject upstream data bypasses around Start * fix(image-list): make optional End text a connection-only input * fix(image-list): isolate unavailable workers during preflight * fix(image-list): bound acknowledgements and configure run deadline * fix(media-sync): preserve output and temp source roots * fix(image-list): own job lifecycle and preserve worker preparation * feat(image-list): let master participate unless orchestrator-only * feat(image-list)!: replace fixed Start extras with growable value_N slots Distributed Image List Start no longer has reference_image, text, strength, seed or per-slot mode dropdowns. It now takes images, mask and up to 10 generic value_N inputs (IMAGE, MASK, STRING, INT, FLOAT, BOOLEAN) that grow via native V3 Autogrow, each with a matching output. - One value is shared by every image; one per image pairs in order; any other count fails before dispatch. Only images is split into frames. - Outputs are declared up front (image, mask, item_index, context, value_1..value_10). web/imageListStart.js hides unused value outputs, mirrors input types, and follows Autogrow compaction so downstream links keep their value. - Image-list protocol bumped to v2; older workers fail preflight. Breaking: saved workflows using the old Start inputs must recreate Start. * fix(serverless): disable Clear saved API key while the worker is enabled The checkbox read "Clear saved API key (disable pool first)", but the panel never defines "pool" and saving with it ticked on an enabled worker was rejected by the backend. - Disable the checkbox while the worker is enabled, with a tooltip saying to turn the worker off first. Also disable it when no key is saved. - Use "worker" instead of "pool" in user-facing serverless errors, the serverless guide and the README entry. * feat(serverless): replace Concurrent jobs with a single Images per run setting - Remove the separate Concurrent jobs field; rename Jobs per run to Images per run (1-16) with a tooltip explaining that Runpod's max workers decides how many GPUs run them. - Backend uses a fixed per-worker limit of 16 outstanding jobs, so all images of a run are submitted at once. Unresolved jobs still count against it. The limit is constant, so it never has to change while jobs are unresolved. - Legacy 'concurrency' in saved configs and older browser tabs is accepted and ignored/dropped; it no longer triggers the busy guard. - Revert the enable toggle and show the reason when the backend rejects it. - Trim a pasted api.runpod.ai/v2/<id> URL to the endpoint ID; plainer endpoint-ID error otherwise. - Confirm before a type change deletes a saved Runpod API key. - Update docs and tests.
177 lines
8.4 KiB
JavaScript
177 lines
8.4 KiB
JavaScript
import { api } from "../../scripts/api.js";
|
|
import { applyProbeResultToWorkerDot, findNodesByClass } from './workerUtils.js';
|
|
import { TIMEOUTS, NODE_CLASSES, generateUUID } from './constants.js';
|
|
import { checkAllWorkerStatuses, getWorkerUrl } from './workerLifecycle.js';
|
|
|
|
export function setupInterceptor(extension) {
|
|
api.queuePrompt = async (number, prompt, ...rest) => {
|
|
if (extension.isEnabled) {
|
|
const hasCollector = findNodesByClass(prompt.output, NODE_CLASSES.DISTRIBUTED_COLLECTOR).length > 0;
|
|
const hasDistUpscale = findNodesByClass(prompt.output, NODE_CLASSES.UPSCALE_DISTRIBUTED).length > 0;
|
|
|
|
const hasImageList = findNodesByClass(prompt.output, NODE_CLASSES.IMAGE_LIST_START).length > 0;
|
|
|
|
if (hasCollector || hasDistUpscale || hasImageList) {
|
|
const result = await executeParallelDistributed(extension, prompt);
|
|
// Immediate status check for instant feedback
|
|
checkAllWorkerStatuses(extension);
|
|
// Another check after a short delay to catch state changes
|
|
setTimeout(() => checkAllWorkerStatuses(extension), TIMEOUTS.POST_ACTION_DELAY);
|
|
return result;
|
|
}
|
|
}
|
|
return extension.originalQueuePrompt(number, prompt, ...rest);
|
|
};
|
|
}
|
|
|
|
export async function executeParallelDistributed(extension, promptWrapper) {
|
|
const traceExecutionId = `exec_${Date.now()}_${generateUUID().slice(0, 6)}`;
|
|
try {
|
|
const hasImageList = findNodesByClass(promptWrapper.output, NODE_CLASSES.IMAGE_LIST_START).length > 0;
|
|
// Image-list v1 uses direct workers only; do not contact paid provider pools.
|
|
const enabledWorkers = hasImageList
|
|
? extension.enabledWorkers.filter(worker => worker.type !== "serverless")
|
|
: extension.enabledWorkers;
|
|
extension.log(`[exec:${traceExecutionId}] Starting distributed execution`, "debug");
|
|
|
|
// Pre-flight health check on all enabled workers
|
|
const activeWorkers = await performPreflightCheck(extension, enabledWorkers);
|
|
|
|
if (hasImageList && activeWorkers.length === 0 && extension.config?.settings?.master_delegate_only) {
|
|
throw new Error("Distributed Image List in orchestrator-only mode requires an active direct worker.");
|
|
}
|
|
|
|
// Case: Enabled workers but all offline
|
|
if (!hasImageList && activeWorkers.length === 0 && enabledWorkers.length > 0) {
|
|
extension.log("No active workers found. All enabled workers are offline.");
|
|
if (extension.ui?.showToast) {
|
|
extension.ui.showToast(extension.app, "error", "All Workers Offline",
|
|
`${enabledWorkers.length} worker(s) enabled but all are offline or unreachable. Check worker connections and try again.`, 5000);
|
|
}
|
|
// Fall back to master-only execution
|
|
return extension.originalQueuePrompt(0, promptWrapper);
|
|
}
|
|
|
|
extension.log(`Pre-flight check: ${activeWorkers.length} of ${enabledWorkers.length} workers are active`, "debug");
|
|
|
|
// Check if master host might be unreachable by workers (cloudflare tunnel down)
|
|
const masterHost = extension.config?.master?.host || '';
|
|
const isCloudflareHost = /\.(trycloudflare\.com|cloudflare\.dev)$/i.test(masterHost);
|
|
|
|
if (isCloudflareHost && activeWorkers.length > 0) {
|
|
// Try to verify if the cloudflare tunnel is actually up
|
|
try {
|
|
const testUrl = `${window.location.protocol}//${masterHost}/prompt`;
|
|
const response = await fetch(testUrl, {
|
|
method: 'GET',
|
|
mode: 'cors',
|
|
cache: 'no-cache',
|
|
signal: AbortSignal.timeout(3000) // 3 second timeout
|
|
});
|
|
|
|
if (!response.ok) {
|
|
throw new Error('Master not reachable');
|
|
}
|
|
} catch (error) {
|
|
// Cloudflare tunnel appears to be down
|
|
extension.log(`Master host ${masterHost} is not reachable - cloudflare tunnel may be down`, "error");
|
|
|
|
if (extension.ui?.showCloudflareWarning) {
|
|
extension.ui.showCloudflareWarning(extension, masterHost);
|
|
}
|
|
|
|
// Stop execution - workers won't be able to send results back
|
|
extension.log("Blocking execution - workers cannot reach master at cloudflare domain", "error");
|
|
return null; // This will prevent the workflow from running
|
|
}
|
|
}
|
|
|
|
const queueResponse = await extension.api.queueDistributed({
|
|
prompt: promptWrapper.output,
|
|
workflow: promptWrapper.workflow,
|
|
enabled_worker_ids: activeWorkers.map((worker) => worker.id),
|
|
workers: activeWorkers.map((worker) => ({ id: worker.id })),
|
|
client_id: api.clientId,
|
|
delegate_master: Boolean(extension.config?.settings?.master_delegate_only),
|
|
auto_prepare: true,
|
|
trace_execution_id: traceExecutionId,
|
|
});
|
|
if (queueResponse?.prompt_id) {
|
|
extension.log(
|
|
`[exec:${traceExecutionId}] Distributed queue accepted by backend (prompt_id=${queueResponse.prompt_id}, workers=${queueResponse.worker_count ?? activeWorkers.length})`,
|
|
"debug"
|
|
);
|
|
return queueResponse;
|
|
}
|
|
throw new Error(
|
|
`[exec:${traceExecutionId}] Backend did not return a prompt_id for distributed queue.`
|
|
);
|
|
} catch (error) {
|
|
extension.log(`[exec:${traceExecutionId}] Distributed execution failed: ${error.message}`, "error");
|
|
if (extension.ui?.showToast) {
|
|
extension.ui.showToast(extension.app, "error", "Distributed Failed", error.message, 5000);
|
|
}
|
|
return null;
|
|
}
|
|
}
|
|
|
|
export async function performPreflightCheck(extension, workers) {
|
|
if (workers.length === 0) return [];
|
|
|
|
extension.log(`Performing pre-flight health check on ${workers.length} workers...`, "debug");
|
|
const startTime = Date.now();
|
|
|
|
const checkPromises = workers.map(async (worker) => {
|
|
if (worker.type === "serverless") {
|
|
try {
|
|
const providerStatus = await extension.api.getServerlessStatus(worker.id);
|
|
if (providerStatus?.ok) {
|
|
extension.log(`Serverless worker ${worker.name} is ready to scale`, "debug");
|
|
return { worker, active: true };
|
|
}
|
|
extension.log(`Serverless worker ${worker.name} is not ready: ${providerStatus?.message || "unavailable"}`, "debug");
|
|
return { worker, active: false };
|
|
} catch (error) {
|
|
extension.log(`Serverless worker ${worker.name} status check failed: ${error.message}`, "debug");
|
|
return { worker, active: false };
|
|
}
|
|
}
|
|
|
|
const workerUrl = getWorkerUrl(extension, worker);
|
|
|
|
extension.log(`Pre-flight checking ${worker.name} at: ${workerUrl}`, "debug");
|
|
|
|
try {
|
|
const probeResult = await extension.api.probeWorker(workerUrl, TIMEOUTS.STATUS_CHECK);
|
|
|
|
if (probeResult.ok) {
|
|
extension.log(`Worker ${worker.name} is active`, "debug");
|
|
return { worker, active: true };
|
|
} else {
|
|
extension.log(`Worker ${worker.name} returned ${probeResult.status}`, "debug");
|
|
return { worker, active: false };
|
|
}
|
|
} catch (error) {
|
|
if (error?.name === 'AbortError') {
|
|
extension.log(`Worker ${worker.name} pre-flight check timed out; assuming active`, "debug");
|
|
return { worker, active: true, uncertain: true };
|
|
}
|
|
extension.log(`Worker ${worker.name} is offline or unreachable: ${error.message}`, "debug");
|
|
return { worker, active: false };
|
|
}
|
|
});
|
|
|
|
const results = await Promise.all(checkPromises);
|
|
const activeWorkers = results.filter(r => r.active).map(r => r.worker);
|
|
|
|
const elapsed = Date.now() - startTime;
|
|
extension.log(`Pre-flight check completed in ${elapsed}ms. Active workers: ${activeWorkers.length}/${workers.length}`, "debug");
|
|
|
|
// Update UI status indicators for inactive workers
|
|
results.filter(r => !r.active).forEach(r => {
|
|
applyProbeResultToWorkerDot(r.worker.id, { ok: false });
|
|
});
|
|
|
|
return activeWorkers;
|
|
}
|