244 — Polynoia: Chinese operator's acknowledgement-loop report and matching source
Reviewed September 6, 2026 UTC.

RESULT
A Chinese TRAE competition entry links an open-source multi-agent coding workspace with a specific post-delivery mention-loop incident account. Current pinned source implements the described acknowledgement suppression. This corroborates a mechanism and published engineering response; the incident's raw run log and model execution remain unverified.

DISCOVERY
https://forum.trae.cn/t/topic/116011
July 13-dated operator demo post links https://github.com/JuneQQQ/polynoia and advertises independent worktrees, task dispatch and merged artifacts. Its setup instructions include demo seeding and local startup, not a public live workspace. The post links screenshots and a video; those media were not inspected in this pass. TRAE hosting and a user-submitted competition entry do not establish ByteDance lab operation.

PINNED EVIDENCE
Repository revision ce6a6fadcd54e232982d1b982d92be46991da711, nontruncated recursive tree with 861 entries. Six fetched files were verified against Git blob hashes:
- docs/sessions/2026-06-overnight-e2e.md
- docs/sessions/2026-06-10-pingpong-and-process-lifecycle.md
- docs/ADR/ADR-022-mention-chain-ack-suppression.md
- scripts/seed_demo.py
- apps/server/polynoia/api/routes.py
- apps/server/polynoia/api/ws_conv.py

INCIDENT ACCOUNT
The June 10 session summary says users observed agents yielding to one another after little work. It describes two chains of post-delivery acknowledgements/mentions reaching depth five, with zero tool activity in the sampled tail. ADR-022 supplies a short illustrative chain and attributes the recurrence to mentions spawning another turn without checking whether the response did useful work. These documents are operator summaries, not an independently recovered conversation transcript.
Pinned routes.py sets the mention-depth limit to three and defines _is_bare_ack_bounce using whether the target is the previous sender and whether the turn did work. ws_conv.py invokes it before spawning the next mentioned agent. That establishes implemented suppression, not that the claimed historical test ran exactly as described. No tests or investigated code were executed here.

OVERNIGHT AND DEMO LIMITS
The overnight summary claims 20 seeded test scenarios passed after repairs, but explicitly says the full per-case log is local and gitignored. Its validation section acknowledges one pre-existing credential-related test failure. No credentials or excluded local logs were sought. Requested model labels, including GLM, are not independent provider attestations.
The inspected seed_demo.py resets the local database and creates five personas, a workspace and an empty group conversation. It specifies zero message records. Therefore merely seeing seed instructions does not establish that the reported conversations were prewritten. Equally, seeded personas and test cases are not an autonomous public swarm. The script was only read and never executed.

INTERPRETATION AND NEXT WORK
This is a concrete Chinese-language operator account of multi-agent interaction failure, accompanied by source that handles that failure class. It remains human-directed software development with unverified raw runtime provenance; it does not establish a Chinese-lab swarm using public scratch sites.
If pursued further, inspect the explicitly linked demo media for task identifiers and artifact/commit joins, or public commit history for the incident fix. Do not equate a product's feature claims, session summary or test pass count with an authenticated deployed fleet.

CAPTURES
244-private/topic.json, tree.json, six pinned files, SHA256SUMS. Public read-only retrieval; no login, agent contact, content creation or investigated-code execution. Existing host access was sufficient.