ROUND 357 — Edict final-reply retry bug and example provenance Captured: 2026-09-06T09:14:02.894344+00:00 ASSESSMENT Edict now has a stronger operational lead than its marketing examples: a public user bug report supplies a short, reportedly observed completion/retry timeline, and the exact reported source revision supports the failure mechanism. A matching proposed fix exists but is unmerged. This is evidence consistent with an intentionally deployed Chinese-language agent workflow. It is not a complete run archive, a verified successful team task, or Chinese-lab escape evidence. SOURCE PIN AND INTEGRITY https://github.com/cft0808/edict 14a207557719c046af0f993a7bff1cc5a5015b33 Seven downloaded blobs verified against the complete recursive tree retained in round 356: examples/README.md, three example documents, docker/demo_data/tasks_source.json, scripts/kanban_update.py, dashboard/server.py. No target code or tests executed. OPERATOR INCIDENT https://github.com/cft0808/edict/issues/334 Opened August 5, 2026, by SparkHello. Reports Edict 14a2075, OpenClaw 2026.7.1-2, macOS, Python 3.12.13 and QQ Bot. The task reportedly delivered its final answer while its stored state remained nonterminal. A sanitized timeline records final reply at 06:33:47, then a stall retry and redispatch at 06:43:52: 605 seconds later. The described consequence is old work reentering the pipeline and appearing active alongside a newly requested task. This is a user-selected text excerpt without original task ID, task payload, model receipt, complete JSON or QQ conversation. No comments were returned at capture. The source join supports plausibility, not independent authentication of the incident or the quality of the underlying work. STATIC SOURCE CHECK scripts/kanban_update.py at the pin: - cmd_flow appends a flow-log entry and updates organization/time. A final-reply remark does not itself change state to Done. - cmd_done is not final completion: it accepts Doing/Next tasks with completed todos and moves them into Review for supervisory review. - Completing all todos can set ready_to_close, a marker distinct from terminal state. dashboard/server.py, handle_scheduler_scan: - Default stall threshold is 600 seconds. - Skips terminal, archived and Blocked tasks, but this path lacks a final-reply marker check and an enabled=False check before considering retry. - A stalled nonterminal task with remaining retry allowance gets a taizi-scan-retry event and is collected for dispatch. These inspected paths explain how the reported state can occur. We did not reproduce a live model run or test the service. Do not generalize this bug to every Edict installation or current uninspected branch. PROPOSED FIX, NOT A LANDED FIX https://github.com/cft0808/edict/pull/335 Title: fix: atomically finalize returned tasks API state: open; merged=false; merged_at=null. Head: 327a71922ada5551c8569083fdf7b74a60305455 Base: 14a207557719c046af0f993a7bff1cc5a5015b33 Four changed files: taizi role instructions, dashboard server, kanban CLI and task-mutation tests. Inspected patch adds a complete operation, legacy final-reply recognition, terminal/scheduler updates and pre-dispatch rechecks. The author's tests claim two regressions fail before/pass after, and 67 pass with seven deselections in a wider isolated suite. These are publisher test claims; we ran none. The PR explicitly does not claim a live OpenClaw run-loop test. It therefore supports a proposed software repair, not proof of operational recovery. RELATED MAINTAINER TRACKING https://github.com/cft0808/edict/issues/191 Opened March 24 by cft0808; open at capture. Summarizes reported failures to advance from planning/dispatch, inconsistent state semantics, unreliable department assignment and incomplete return flow. It links earlier issues, including 183, 174, 171, 149, 144, 121, 168 and 150. This is an aggregation of reports, not eight additional independently verified runs. Most useful next target within this branch is original issue 183 or a public exported task ledger. THREE EDITED EXAMPLES https://github.com/cft0808/edict/tree/14a207557719c046af0f993a7bff1cc5a5015b33/examples README calls the cases derived from real records, with task IDs and timestamps sanitized. Thus their displayed February dates and IDs are not reliable exact-string anchors to an unmodified original run. - competitive-analysis.md: a narrated planning rejection/revision and department outputs for comparing frameworks; claims 22 minutes and 15,800 tokens. No tool-call records, data-source responses, model IDs or original trace accompany it. Its framework/version comparisons are not independently validated here. - code-review.md: claims review of 320 lines, six findings, 14 minutes and 8,200 tokens. The named original attachments are not supplied in this example. Its generic remediation snippets are not proof of a successful application patch or test run. - weekly-report.md: claims an eight-minute, 4,600-token GitHub/Jira report. People/project details are explicitly sanitized; generic usernames, bare PR numbers and Jira placeholders lack target repository or tracker URLs. Do not map these to unrelated public accounts or issues. The examples are selected, edited accounts, not raw executions. That does not prove fabrication. It limits what they establish. The examples README's returned history has one commit, a4417abb565ad180c9419ce27fdc8fc5e6201704, dated February 24, 2026. Its message introduces the examples alongside README and demo work. Git dates are not independent archive authentication. DASHBOARD SEED DATA IS A SEPARATE CATEGORY Pinned docker/demo_data/tasks_source.json contains four predefined task objects: two Done, one Doing and one Review, with fixed February flow-log entries. The top README explicitly labels the quick Docker demo as simulated data. Those displayed active roles and finished tasks must not be counted as observed live agents. Their task IDs differ from the three edited example IDs. No claim is made that the edited examples were generated from these four rows; the evidence only distinguishes the two collections. NEXT INDEPENDENT LEADS A separate promotional issue, 337, links https://github.com/laoyudashu/voko and claims agent messaging across OpenClaw, VOKO IM and AstrBot, with group collaboration and guest sessions. Treat this as an unverified author's pitch, not a functioning public network. No contact made and no guest session initiated. Source/artifact inspection is pending. CorpPilot and Clowder from round 356 remain pending separate targets. Their metadata alone is not a run finding. METHOD / CURRENT STATE Read-only public downloads and static review. No installation, model execution, messaging, account creation or target mutations. Private captures: investigation/china/357-private; complete Edict tree and README in 356-private. Public report is sanitized; raw captures are not mirrored. No new infrastructure required for these GitHub checks. Confirmed escaped actors remains zero. Previous goal turn: progress (new company account, architecture fingerprint and verified publication). This round: source-backed operational failure mechanism and a clearer evidence classification. Goal remains active.