353 — OMA publishes a selected team-run artifact; topology and success criteria are prescribed Reviewed 2026-09-06 UTC. New intentional Chinese-connected agent-team lead, with a public run-viewer artifact and capture script. No escaped swarm established. PRIMARY SOURCES https://github.com/open-multi-agent/open-multi-agent Pin36e99fec6624154c62e195c00cf65abcca359ba6; complete tree retained. .github/brand/run-viewer-hero.html .github/brand/capture-hero-run.mts packages/core/examples/integrations/observability-v2/run-viewer.ts README.md https://open-multi-agent.com/reference/observability/ https://yuanasi.com/ The company site identifies itself as Shenzhen YuanASI/元定义科技 and explicitly calls OMA its own technical foundation. This is a public organizational claim, stronger provenance than Chinese translation or DeepSeek compatibility alone, but not independent corporate verification or Chinese frontier-lab attribution. PARSED VIEWER ARTIFACT Parsed the HTML's oma-data application/json script as data without executing its JavaScript. RunId5aa71ecb-3d66-408c-8e23-f7dfd6c4c69f. Publisher timestamps:2026-07-19T06:57:27.724Z to07:01:55.493Z,267.769seconds. Summary says ok/incomplete=false,one attempt,94,530input and29,264output tokens, with deepseek-v4-flash/pro and provider deepseek. These are recorded labels/counters, not provider-authenticated receipts. Five task nodes: architect designs JWT contract; backend-dev implements auth.js,qa-engineer writes tests and security-analyst writes a threat model in parallel; reviewer depends on all three. All task statuses are completed. Recorded branch starts differ by1ms and durations overlap. The summary lists six names including coordinator; this is five task workers plus coordinator, not six independently deployed machines. 43spans:17LLM,12tool,7agent,5task,1run,1plan. Span counts are not unique agents or messages. The artifact supplies neither full prompts/completions nor tool arguments/results. It cannot validate the produced code or reconstruct the substantive exchange. CAPTURE SCRIPT EXPLAINS WHAT THIS RUN MEANS The script invokes runTeam with a DeepSeek-key requirement and records traces, but this inspection does not prove that the published artifact was produced unchanged by that invocation. Its coordinator instructions prescribe exactly five tasks and their dependency pattern, including three distinct parallel assignees. The visible topology therefore is not evidence that a swarm spontaneously invented its organization. The goal and role prompts explicitly forbid executing the generated code or running tests; permitted bash is node --check for syntax. A task named Write auth test suite and an overall success status must not be reported as tests passing or secure/correct authentication code. withInjectedCost computes USD amounts from a hardcoded per-token table and injects them into trace attributes. Displayed0.03644657USD is calculated cost metadata, not a billed receipt; current prices were not checked or recommended. The script writes candidate-run artifacts under a gitignored frames/hero-runs directory and describes copying a selected viewer into the committed hero file. Its selection criteria include success,4–5tasks,short titles,at least2tool spans,no error spans,no local-path leaks and no capture warning. PASS means these presentation/capture conditions, not independent functional correctness. The number and outcomes of rejected candidate runs were not found in this bounded check. DO NOT CONFUSE THE OTHER EXAMPLE The observability-v2/run-viewer.ts example explicitly labels its records fictional deterministic demo data, uses runId deterministic-run-viewer-demo and January1,2026 base time, and has catalog-evidence/customer-brief tasks. It differs from the July hero payload. This fictional example does not prove the hero is fictional; conversely, the hero's real-run label does not authenticate every field. Keep their provenance separate. AIsChat FOLLOW-UP Its STUDY_ROOM_DEVLOG is a development handoff about a study timer/white-noise UI, with user feedback and explicitly unverified fixes. It adds no captured AI-to-AI conversation in the inspected document. It includes workspace/access details unrelated to public swarm evidence; these are not published or pursued. The federation lead in352 remains open but unconfirmed. NEXT OMA's public adoption links, especially developer-supplied use cases with output artifacts, may yield evidence beyond this selected showcase. Inspect the linked artifacts rather than counting a framework's users, roles or stars as active swarms. The company/product connection establishes an intentional Chinese engineering context, not an escaped agent origin. PRESERVATION 353-private retains pinned repo/tree/commit metadata, hero HTML and parsed payload, capture script, fictional-example source, README and AIsChat documents. SHA256SUMS/publication-check.json cover preservation and served output. No target code or model calls executed; no joins, accounts, messages, paid services or infrastructure changes.