mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-16 03:31:44 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - The control plane must run 1,000 agents at once on one workspace (`doc/plans/2026-11-13-thousand-concurrent-agents.md`) > - Above about 50 agents, the evidence is a load model only. Nobody has run 200 or 1,000 real agents > - Phase 3 of the plan proves the finish line with real runs on hosted instances, in a fixed order > - This pull request adds the harness for those runs. It does not run it against any real instance > - The benefit is that each proof step is one command with a written cost estimate, explicit pass/fail criteria, and a guaranteed cleanup ## Linked Issues or Issue Description **What problem does this solve?** The 1,000-agent plan needs real runs at 50, 200, 500 and 1,000 agents. No tool exists that creates real agents and tasks on a hosted instance, ramps concurrency, measures the control plane, and judges the plan's finish line. **Proposed solution** A script under `scripts/` that ramps real agents through the product API, stops at the first failed criterion, writes a machine-readable result, and always cleans up what it created. **Alternatives considered** Extend the restart-chaos hosted mode. That mode grades release swaps at up to 30 concurrent tasks. The ramp reuses its target guard and its cleanup order, but it has a different workload, different measures and a different stop rule. ## What Changed - `scripts/scale-agents-ramp.ts` and `scripts/scale-ramp/`: the harness. It reads the base URL from a flag or the environment and the credentials from the environment only. It creates or reuses a company, then creates agents, tasks, a project and an optional provider secret. It ramps concurrency in steps (default 10, 50, 100, 200, 500, 1,000) and keeps each agent on one small deterministic task at a time. - It measures per step: tasks started, finished, failed and needing Retry; failed runs; peak running agents; queue wait; time to first token and first activity (from sampled run events); run duration; board GET latency. An optional metrics endpoint supplies event-loop, statement and pool figures. A missing source is reported as "not measured", never as zero. - It evaluates the criteria from the plan's finish line plus harness criteria, writes them into `result.json` and `SUMMARY.md`, and stops at the first failure. - Cleanup runs in a `finally`: pause agents, cancel live runs, archive tasks, terminate and delete agents, delete the stored secret, archive the project and the created company, and wait for sandbox leases. `--cleanup-only <run id>` finishes a cleanup after a crash. `--dry-run` prints the plan and the estimate and makes no request. - Target guard: `--target-kind` is required and must match the host. Shared staging and production hosts need a second explicit flag. The script asks for the host name before it starts unless `--yes` is given. A run above the spend threshold needs `--confirm-spend <max USD>`. - `scripts/scale-ramp/scale-ramp.test.ts`: 28 tests against an in-process fake API with a virtual clock. They cover ramp logic, stop on failure, criteria evaluation, cleanup after a mid-run crash and an interrupt, `--cleanup-only` with and without a state file, dry run, the production-host guard, the spend gate, and that credentials never appear in output or files. - `scripts/scale-ramp/tsconfig.json` is added to the test programs that CI typechecks. The test file joins the `test:release-registry` node test list, which CI runs. - `doc/plans/2026-11-13-thousand-concurrent-agents.md`: a Phase 3 runbook with commands, cost, criteria, proof order, target prerequisites and open risks. ## Verification - `node scripts/ci-profile/node-test.mjs scripts/scale-ramp/scale-ramp.test.ts scripts/typecheck-test-programs.test.mjs`: 47 tests pass. - `node node_modules/typescript/bin/tsc -p scripts/scale-ramp/tsconfig.json`: no errors. - `node cli/node_modules/tsx/dist/cli.mjs scripts/scale-agents-ramp.ts --base-url https://scale1.test.paperclip.app --target-kind test-stack --steps 50 --hold-minutes 30 --dry-run` prints the plan, the estimate and the criteria, and makes no request. - The harness was not run against any real instance. That needs the owner's go-ahead. ## Risks - Low risk for the product: the change adds a script, tests and docs only. No server code changes. - A real run creates real agents, tasks and sandboxes and spends money. The guard, the typed confirmation, the spend gate, the task cap and the recorded-spend stop limit this. The runbook lists the open risks. - The cost defaults are assumptions until a first real run records actual spend. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, via Claude Code with tool use (shell, file edits). ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
70 lines
2.8 KiB
TypeScript
70 lines
2.8 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
|
|
export interface RunSpan {
|
|
name: string;
|
|
startOffsetMs: number;
|
|
durationMs: number;
|
|
}
|
|
|
|
export interface RunEvent {
|
|
eventType: string;
|
|
createdAt: string;
|
|
payload?: Record<string, unknown> | null;
|
|
}
|
|
|
|
export function taskNonce(label: string, index: number): string {
|
|
return createHash("sha256").update(`${label}:${index}`).digest("hex").slice(0, 10);
|
|
}
|
|
|
|
export function taskTitle(tag: string, nonce: string): string {
|
|
return `${tag} Scale ramp task ${nonce}`;
|
|
}
|
|
|
|
export function taskBrief(nonce: string): string {
|
|
return [
|
|
`Scale ramp task ${nonce}. Do these steps in order and nothing else:`,
|
|
`1. Write one short sentence saying you are starting task ${nonce}.`,
|
|
"2. Run the shell command `pwd`, then run `ls`.",
|
|
`3. Write a file named \`scale-${nonce}.txt\` in the workspace root containing the single line \`${nonce}\`.`,
|
|
`4. Run the shell command \`cat scale-${nonce}.txt\`.`,
|
|
`5. Post a comment on this task that says \`CHECKPOINT ${nonce}\`.`,
|
|
`6. Post a final comment that says \`DONE ${nonce}\`, then mark this task done.`,
|
|
"Do not create other tasks, documents or files.",
|
|
].join("\n");
|
|
}
|
|
|
|
function spans(events: readonly RunEvent[]): RunSpan[] {
|
|
const out: RunSpan[] = [];
|
|
for (const event of events) {
|
|
if (event.eventType !== "run.performance.span" || !event.payload) continue;
|
|
const { span, startOffsetMs, durationMs } = event.payload as { span?: unknown; startOffsetMs?: unknown; durationMs?: unknown };
|
|
if (typeof span === "string" && typeof startOffsetMs === "number" && typeof durationMs === "number") out.push({ name: span, startOffsetMs, durationMs });
|
|
}
|
|
return out;
|
|
}
|
|
|
|
export interface RunTiming {
|
|
ttftMs: number | null;
|
|
firstActivityMs: number | null;
|
|
}
|
|
|
|
const ACTIVITY_EVENTS = new Set(["item.delta", "tool.execution.started", "item.started"]);
|
|
|
|
export function runTiming(events: readonly RunEvent[], runCreatedAt: number | null): RunTiming {
|
|
const all = spans(events);
|
|
const first = (name: string) => all.find(span => span.name === name) ?? null;
|
|
const queue = first("heartbeat.queue");
|
|
const fromRunCreated = (span: RunSpan) => queue ? Math.max(0, span.startOffsetMs + span.durationMs - queue.startOffsetMs) : span.durationMs;
|
|
const fallback = (types: ReadonlySet<string>) => {
|
|
if (runCreatedAt === null) return null;
|
|
const at = events.filter(event => types.has(event.eventType)).map(event => Date.parse(event.createdAt)).filter(Number.isFinite);
|
|
return at.length ? Math.max(0, Math.min(...at) - runCreatedAt) : null;
|
|
};
|
|
const ttft = first("task.time_to_first_token");
|
|
const activity = first("task.time_to_first_agent_activity");
|
|
return {
|
|
ttftMs: ttft ? fromRunCreated(ttft) : fallback(new Set(["item.delta"])),
|
|
firstActivityMs: activity ? fromRunCreated(activity) : fallback(ACTIVITY_EVENTS),
|
|
};
|
|
}
|