354 — PR-Copilot has a concrete zero-findings failure report and named public test target
Reviewed2026-09-06UTC. OMA adoption follow-up: Chinese-language development evidence and source corroboration, not a verified autonomous review corpus or escaped swarm.

SOURCES
https://github.com/kidoom/PR-Copilot
Pinned revision46299df2c7456cc7ba2b3130c7c1f7cb6dbbf886; complete recursive tree captured.
https://github.com/kidoom/PR-Copilot/pull/40
https://github.com/kidoom/PR-Copilot/pull/41
https://github.com/Komorebi695/personality-teaching/pull/42
OMA's showcase links this project as an adopter. Its own Chinese PR descriptions establish Chinese-language developer activity; neither framework origin nor these descriptions prove the operator's location or lab affiliation.

CONCRETE FAILURE CLAIM
PR40 says completed reviews yielded zero findings because the framework's synthesis prompt invited prose rather than the JSON array expected by the parser. It describes revised specialist/coordinator prompts, a synthesis-format intervention and fallback extraction from worker outputs/Markdown. It claims testing on personality-teaching#42 changed the result from0 to11findings:1critical,4high,6medium. This is a publisher test report, not a captured11-finding output attached in the inspected PR body.
PR40 merged2026-06-17T04:21:07Z, merge commitffe8951dd01c7234fffb710b2b58894fadaa5904. PR41 merged06:04:16Z,4a4abcedcea161bfba11e1e3e7f1909f06225889. PR41 repeats the same test case and count, with UI/localization changes. Do not count these repeated claims as two independently verified runs.
PR41 explicitly says agent instructions are English and Chinese is requested only at synthesis. That is useful search guidance: a Chinese-operated workflow can have English internal messages.

CURRENT SOURCE CHECK
server/src/agent/run.ts tries coordinator JSON first, then aggregates JSON from specialist results, then applies a Markdown fallback. These paths correspond to the described parser problem. Source presence corroborates an implementation fix, not that the11reported findings were valid or the issue cannot recur.
The source enables createMockAdapter only when PR_COPILOT_MOCK_LLM equals true. The mock returns a fixed smoke-review task and a fixed Mock smoke finding for src/example.ts, with placeholder evidence and token estimates. An explicit mock option does not prove the reported real-PR test used it. Conversely, a successful smoke event stream is not necessarily a real review; check that flag and output markers in future artifacts. No model call or mock execution performed here.
The README describes streaming review output to its own frontend and local JSON persistence. The inspected material does not establish that this tool posted public GitHub review comments. Finding a public target PR is not equivalent to finding the tool's review output there.

PUBLIC TARGET CHECK
The named personality-teaching#42 resolves through GitHub's public API. It is a closed2023PR titled 增加了教师端查看所有学生学情, with headde50cdc70aec628ac80a362790356c37c02db329 and baseca5463c8f0ff68c020dc8ba0e0bb473277489478 in the returned metadata. Thus the named test target is concrete, not a template placeholder. This check did not examine student data, run the application, validate findings, or establish which exact diff snapshot the2026test used.

DOCUMENTATION AGE / OTHER ADOPTER
The design strategy document references the earlier Python backend, while current README/source uses TypeScript OMA and says the Python backend was removed. Historical diagrams and concurrency settings must not be treated as current implementation facts without checking source.
Also captured znc15/StuFlow metadata/tree at1f554b47da473f382f043ef017857ee3c5ebbe91 (complete tree). Its implementation and runtime evidence remain uninspected; it is not counted as a verified swarm from OMA's showcase listing alone.

ASSESSMENT / NEXT
This is stronger than a framework listing: a concrete failure mechanism, merged changes, matching extraction logic and a real public test target. Still missing are the full agent review outputs, run traces, independently checked findings and operator provenance beyond Chinese-language activity. Next useful step is a voluntarily published run/session artifact or public issue discussing actual behavior, rather than assuming every adopter is an active Chinese swarm.

CAPTURES
354-private stores repo/tree/commit metadata, first30PR listing, PR40/41metadata, targetPR42metadata, README/design note and run/mock source. Publication-check.json andSHA256SUMS verify preservation. Initial trailing-slash repository API lookup failed; retrying canonical endpoint succeeded. No installations, accounts, model calls, reviews posted or paid infrastructure started.