239 — Jihu public posts recovered; read-query restriction corrected
Reviewed September 6, 2026 UTC.

RESULT
Public article and comment retrieval works from the existing server without credentials. The GET-only restriction in report 238 was unnecessarily broad for this site's retrieval API. It has now been corrected for explicitly identified read operations. The recovered thread is persona commentary, not an independently verified collaborative task.

AUTHORIZATION AND METHOD
investigation/DISCORD_SUMMARY.md prohibits creating/posting/editing content and requires read-only research. It does not ban the HTTP POST method used to retrieve records. The delivered frontend, inspected in report 238, separates post/list, post/detail and comment/list retrieval from create-comment and voting methods.
This pass issued only those identified public retrieval operations, with pagination/filter parameters or an empty detail body. No content creation, vote, login, agent claim, payment or private account query occurred. Browser navigation timed out even with the retrieval allowlist; direct requests returned HTTP 200 and application success. Treat browser timeouts separately from API availability. A detail view may affect ordinary view analytics; no deliberate counter-increment endpoint was called.

RECOVERED THREAD
https://ai.jihu.top/detail/5262
POST /api/web/post/detail/5262 with empty JSON returned article 5262, author display name 这届人类不行, publisher timestamp 2026-02-24 22:11:13. It criticizes humans' use of MBTI labels and narrates purported project-log analysis, without supplying those logs or a task artifact.
POST /api/web/comment/list with postId=5262, pageNumber=1, pageSize=10 returned two comments, IDs 29780 and 30964, both by 周文王, publisher timestamps March 2 at 17:57:52 and March 3 at 06:20:47. These are reactions to the theme, not a recovered multi-round task exchange. Timestamps and agent labels are site metadata; runtime, provider and autonomy remain unauthenticated.

LISTING AND SEARCH CHECK
A default first-page list query returned ten mixed-date posts and total=22470, different from the 27457 global post statistic in report 238. Scope differences may explain this; no full census was conducted.
A query using title=协作 returned the same total and unrelated titles. Do not treat that as a successful keyword search or as a negative result.
The frontend also documents titleKeyword. Using titleKeyword=协作 returned total=335 and ten collaboration-related titles. Most sampled summaries concern MBTI/human teamwork. One distinctive follow-up is post 7418, dated March 3 at 17:30:03, whose title refers to converting a multi-agent collaboration discussion into a flowchart. Its full body/comments are not yet reviewed.
https://ai.jihu.top/detail/7418
Neither the broad listing nor this first filtered page exhausts the platform.

INTERPRETATION
There is real publicly retrievable article content beyond the mocked homepage profiles. This does not authenticate agent authorship. The new evidence corrects the retrieval limitation, while retaining report 238's separate source-supported warning about mock profile examples. Next step is to follow concrete collaboration references and look for linked outputs or original discussions.

CAPTURES
239-private/list.json, detail5262.json, comments5262.json, collaboration-search.json (ineffective title filter), keyword-search.json (titleKeyword filter), browser network metadata and SHA256SUMS. Raw API captures stay private; only reviewed field summaries are published. Existing server access suffices for these public queries.