docs: refresh the QA plan against the live task list (V-459)

The plan named 40 task numbers on 2026-08-01. Ten open QA tasks were missing
and two of the named ones had closed, so the 44-of-50 header was wrong twice
over.

- header is 42 of 50, and every open task now appears
- placed the ten unlisted QA tasks: 14, 248, 249, 250, 258, 283, 284, 285,
  286, 323
- new Operations sitting for 249 and 250, and a Query sources sitting for
  258 and 286
- 14 and 284 join housekeeping: both are gated on something unbuilt
- dropped the 317 and 354 rows, closed 01-08-2026, with one line saying what
  landed
- 319's gate recalibration is done; what is left is re-deriving QueryMinMargin
- 323 is down to the 60s startup timeout arm after PR #90
- new "Not this repo" section for 358 (Hexis) and 362 (training workspace)
- router latency is ~27x, not 90x; the 2.7s p50 was contention, not the model

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1

docs/qa.md

@@ -1,13 +1,18 @@
 # QA plan: checking Maven properly
 
-*Last verified: 2026-08-02 @ 7079a24. Living doc: correct it in place, do not append.*
+*Last verified: 2026-08-02 @ 5c05163. Living doc: correct it in place, do not append.*
 
 Written 2026-08-01, after the 35-PR stack landed and the box came back up.
+Refreshed 2026-08-02 against the live list, after PRs #85-#90.
 
-44 of the 50 open Vikunja tasks are `QA:` tasks. They are verification work, not
+42 of the 50 open Vikunja tasks are `QA:` tasks. They are verification work, not
 build work. Most sat unverifiable while Maven was down for 11 days. That
 blocker is gone.
 
+The plan as written on 2026-08-01 named 40 task numbers. Ten open `QA:` tasks were
+missing and two of the named ones had closed. Every open task now appears below,
+the eight non-QA ones in the last two sections.
+
 This plan orders them by what unblocks what. Do sessions 1 and 2 first. Almost everything
 downstream assumes the voice loop works, and nobody has confirmed that since
 the redeploy.
@@ -56,25 +61,25 @@ session quality), **321** steps 3-5 (quiet mode), **288** (STT fixtures).
    `snoozed`. Say `потом` again with nothing pending: it must route as an
    ordinary utterance, not be swallowed.
 8. Wait for the water nudge, then say `выпил воды`. Expect the ordinary fact
-   reply and nothing extra — she must not congratulate you. Check
+   reply and nothing extra. She must not congratulate you. Check
    `/notifications`: the row reads `acted`. Then trigger another nudge and say
-   `готово`; expect `отлично, отметила.` and the same outcome.
+   `готово`. Expect `отлично, отметила.` and the same outcome.
 9. Note anything where she is slow, cuts off, or talks over herself. That is
    287's whole content and it has no written acceptance criteria yet.
 
-**319 is fixed** (01-08-2026). Single-word Russian utterances no longer come
+**319's single-token bug is fixed** (01-08-2026). Single-word Russian utterances no longer come
 back as `не совсем поняла — можешь переформулировать?`. `привет` and `поужинал`
 both pass now: `thinSingleToken` spares social singles and any token carrying a
-verb ending, and only thins a bare nominal like `вода`. If a one-word utterance
-still gets clarified during the smoke test, that is a new case for the lexicon,
-not the old bug.
+verb ending, and only thins a bare nominal like `вода`. A one-word utterance that
+still gets clarified in this session is a new case for the lexicon, not the old bug.
 
 ---
 
 ## Session 2: measurement (half a day, mostly waiting)
 
-Closes or advances: **320** items 2-4, **278** (make the eval lab routine),
-**319** (gate recalibration).
+Closes or advances: **320** items 2-4, **278** (make the eval lab routine).
+Also **248** (memory evaluation), **319** (the margin gate) and **323** (the
+startup timeout arm).
 
 The resident llama-server cannot be reached by the eval harness. It binds
 `--host 127.0.0.1 --port 0` inside the container, so the port is kernel-assigned
@@ -99,14 +104,25 @@ make eval-recall
 
 A large miss against 72.7% means the deploy differs from the bench harness.
 
-Two things to decide while the numbers are in front of you:
+Then three things to decide while the numbers are in front of you:
 
-- **319's gate recalibration.** The single-token rule needs narrowing or
-  dropping. This needs your judgement, not a threshold sweep. The fixture and the
-  daemon disagree about what is correct on two of the three false clarifies.
+- **319's gate recalibration is done.** 359 gave the LLM path a real confidence
+  signal. `thinSingleToken` was narrowed on 01-08-2026, and agenda questions moved
+  to stage 0. Missed clarify sits at 1 of 6 and false clarifies at 2. What is left
+  on 319 is item 2 point 2: re-derive `QueryMinMargin`, or show the distribution
+  the hand-picked `0.008` came from.
 - **278's real ask** is making the eval lab routine rather than building it. It
   is built. Decide whether it runs on a timer, on every merge, or on demand, and
   the task can close.
+- **248** is the memory evaluation loop. It ships, it writes notes, and it cannot
+  speak. `make eval-recall` covers the retrieval half. The open question is whether
+  a written evaluation nobody reads is worth the tick.
+
+**323 is down to one check.** PR #90 covered the spawn path and took phraser
+coverage to 76.9%. Only the 60s startup timeout arm is untested, because testing it
+needs a `StartupTimeout` field on `Config` rather than a test-only hack. While you
+are on the box, time a cold 1.7B load off spinning disk. If it runs near 60s, the
+default is too tight and the field earns itself twice.
 
 Item 4 of **320** needs a permission I do not have. Kill the `llama-server`
 pid under `maven-mavend-1`, post a turn, and confirm it still completes
@@ -119,10 +135,20 @@ check that the failure floor catches a mid-session model death.
 
 These need real use rather than a command, grouped by what one sitting covers.
 
-**Morning and delivery** (**280**, **281**, **128**, **282**): open `/morning`,
-walk the seven required behaviours, then check the four interruption outcomes
-and the digest gap. **282** needs the `desk_active` script enabled on the desk
-PC first, which is **15** and needs you at that machine.
+**Morning and delivery** (**280**, **281**, **128**, **282**, **283**, **285**):
+open `/morning`, walk the seven required behaviours, then check the four
+interruption outcomes and the digest gap. **282** needs the `desk_active` script
+enabled on the desk PC first, which is **15** and needs you at that machine.
+**283** is the event intake envelope every reach shares, so a delivery check
+exercises it whether you name it or not. **285** is not verification: the bridge
+framework works and the remaining ask is more adapters. Decide which reach comes
+next, or park it.
+
+**Query sources** (**258**, **286**): ask her something the RSS feeds answer and
+something only a ZIM answers, with the search block on. Live search leads and the
+ZIMs are the fallback since 02-08-2026. A ZIM answer to a current-events question
+means the search leg failed silently. **286**'s remaining half is doc and
+git ingestion, which is build work, not a check.
 
 **Tasks and calendar** (**129**, **130**, **127**, **126**, **246**): capture a
 task by voice, confirm it lands, check prioritisation ordering is not nonsense.
@@ -138,17 +164,27 @@ concluding anything.
 logged clean at boot. **276** is the degraded-mode suite, which means taking
 siblings down on purpose. Worth doing while you are already in there.
 
+**Operations** (**249**, **250**): these bite hardest if they are broken, and
+nobody has pulled either lever on this box. Roll **249** forward and back once,
+then swap `phraser.model_path` and confirm **250** reloads without a restart. Do
+this sitting last, because both checks can take the box down.
+
 ---
 
 ## Housekeeping (one sitting, no box needed)
 
-Four QA tasks will not close no matter how long they sit, because they are
+Six QA tasks will not close no matter how long they sit, because they are
 gated on something that does not exist:
 
 - **125** zenmoney: needs a token you have not minted.
 - **256** Home Assistant: needs HA configured.
 - **257** Bluetooth: BLOCKED, no bluez on the box. Says so in the title.
 - **288** STT golden audio: needs fixtures generated.
+- **14** cold-start unlock: the `-wrapped-key-file` seam exists, the passkey to L3
+  half does not. `lockedAPI` was deleted as dead code in PR #50, so there is
+  nothing to verify.
+- **284** replayable full-system simulator: nothing is built. This one is a
+  design task wearing a `QA:` prefix.
 
 Relabel these so they stop reading as backlog. They are not verification work
 that is pending, they are work that has not started.
@@ -171,16 +207,32 @@ Not QA. These are blocked on a decision or a credential only you have.
 | 355 | Deploy the Hexis auth change. Was blocked on Maven being under construction, which it no longer is. The client half is vendored and wired. |
 | 357 | Decide whether entity-existence validation is the permanent target guard or whether blessing lands in Nexus. |
 | 275 | Hexis native API and MCP parity. |
-| — | Decide on `-require-stepup`. Making it the default needs WebAuthn configured first, or it locks you out of your own admin surfaces. See **317**. |
-| — | Three nginx sites bind wildcard `:80` (`acme.conf`, `matrix`, `panel`), so the ecosystem's bind-level protection is not in effect and `allow`/`deny` is carrying it alone. See **354**. |
+| — | Decide on `-require-stepup`. Making it the default needs WebAuthn configured first, or it locks you out of your own admin surfaces. |
+
+317 and 354 closed on 01-08-2026. The step-up gate now covers `POST /api/chat` and
+`/routines`, and the nginx template is locked down with a `maven.<domain>` block for
+mavweb. The `-require-stepup` default is still your call.
+
+---
+
+## Not this repo
+
+Two open tasks sit on the Maven board and are not Maven work. Move them or note
+where they land, so the board stops reading as 50 things Maven owes.
+
+- **358** replace the rowid execution cursor with a real seq column. This is Hexis,
+  and it must land before any execution retention or pruning does.
+- **362** mirror the router prompt reorder into the relabelling prompt. This is the
+  training workspace, enforced by `llm/check_prompt_parity.py` there, not here.
 
 ---
 
 ## Suggested order
 
 1. Session 1. If the voice loop is broken, nothing else matters.
-2. The `-require-stepup` and Kuma decisions. Five minutes, unblocks **317** fully
-   and **16**.
-3. Session 2. The numbers tell you whether the router is worth its 90x latency.
+2. The `-require-stepup` and Kuma decisions. Five minutes, and it unblocks **16**.
+3. Session 2. The numbers tell you whether the router is worth its ~27× latency.
+   The 90× figure that stood here came from a 2.7s p50 that was contention, not
+   the model. Real p50 is 825ms against the classifier's 31ms.
 4. Housekeeping. Cheap, and it makes the remaining backlog honest.
 5. Session 3, split whichever way suits you.