From 1e82f3adbacc8509758f298b1dc1c7d76039c8fd Mon Sep 17 00:00:00 2001 From: operator-main Date: Sun, 4 Oct 2026 20:09:56 +0000 Subject: [PATCH] Document 2026-10-04 followup fix set in LOOP-MANAGEMENT.md (backfill semantics, final_nudge_target, placement gate, multi-RESULT) --- docs/LOOP-MANAGEMENT.md | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/docs/LOOP-MANAGEMENT.md b/docs/LOOP-MANAGEMENT.md index 29e1f8d..fef267b 100644 --- a/docs/LOOP-MANAGEMENT.md +++ b/docs/LOOP-MANAGEMENT.md @@ -158,6 +158,42 @@ super loop remediate [--dry-run] - `POST /api/box/loop/resolve` → Body: `{"dm_id": "...", "note": "..."}`. - `POST /api/box/loop/remediate` → Runs progressive remediation cycle. +#### Followup record fields & nudge→reply matching (2026-10-04 fix set) + +Followup records in [`followups.json`](file:///home/super/Projects/NetVM/followups.json) carry two fields +introduced by the 2026-10-04 reliability fix set (see `docs/SIDECHAT-RELIABILITY.md`): + +- **`thread_uuid` backfill** — when a followup is created but the sidechat thread + autoprovisioning failed (no UUID captured), the sweeper retries on each nudge. + Once a nudge send succeeds with autoprovisioning (`sidechat_autoprovisioned` + in `dm-log.jsonl`), the sweeper backfills `thread_uuid` into the record. Once + set, the field is **never overwritten with null** — a followup with a null + `thread_uuid` can never match a reply, so it would ghost-nudge then escalate + on a thread that never existed. +- **`final_nudge_target`** — set to `"main"` when the final nudge routes to the + main chat instead of a sidechat (routing policy: nudge in-thread first, main + only on the final attempt). + +**Nudge→reply matching matrix** (implemented in `bin/response-harvester.py`): + +| Nudge routing | Reply location | Resolves when | +|---|---|---| +| In-thread nudge | Assistant reply in the thread whose UUID == `thread_uuid` | UUID match | +| Final nudge → main | Assistant reply in main chat | `final_nudge_target == "main"` | +| Any | Reply in a different thread | Never auto-resolves (manual `loop close`) | + +The sweeper also backfills `thread_uuid` immediately after a successful nudge +send when the send itself autoprovisioned the thread, so later replies match. + +**`dm.py` placement assertion** — before sending to a sidechat, `dm.py` fails +closed (loud refusal, no `verified:true`) if the post-navigation browser URL +does not contain the target thread UUID. The `"main"` target is exempt. This +catches silent `sidechat use` failures and wrong-thread sends. + +**Multi-`[RESULT]` harvesting** — the harvester processes **every** `[RESULT …]` +marker in a message (previously only the first), so replies that batch several +job results each resolve their followup and trigger their own chain step. + --- ## 4. Background Services & Daemons @@ -212,3 +248,4 @@ python3 -m unittest discover -s tests -v - [`tests/test_modulate_strategy.py`](file:///home/super/Projects/NetVM/tests/test_modulate_strategy.py): Hierarchical override cascade and dynamic evaluation. - [`tests/test_loop_health_remediation.py`](file:///home/super/Projects/NetVM/tests/test_loop_health_remediation.py): Progressive remediation, diagnostics, and loop reconstruction. - [`tests/test_main_nav.py`](file:///home/super/Projects/NetVM/tests/test_main_nav.py): Sidechat navigation and Main Chat policy enforcement. +- [`bin/tests/test_followup_fixes.py`](file:///home/super/Projects/NetVM/bin/tests/test_followup_fixes.py): DM-machinery harness (25 tests) — sweeper backfill, final-nudge routing/marking, harvester matching matrix, multi-`[RESULT]` extraction, and the `dm.py` placement assertion (incl. main-exempt).