docs(records): Sage lead handover, rows 23-25 state, row 8 stub, BUILD-LOG rebuilt on HEAD
Records Jason's 2026-09-26 ruling: Sage leads the project, Darkwing is a collaborating seat, development stays in T3, and the old ~/.mosaic fleet is being retired. The lead role adds no push, merge or deploy authority. - QUEUE rows 23-25 show their commits and pushes; row 8 links a parked stub brief listing the rulings Jason must make before fleet seats move. - Shared records from Darkwing (rows 6, 16, 18, 22, #1511, #1512) and Dewey (row 5) that were waiting on one owner for the shared files. - DEFERRED: T3 headers counted as human in the ledger (#1506), #1509 engine test leak and busy gap, #1512 re-run outcome. - BUILD-LOG.md rebuilt as HEAD plus the uncommitted entries; the working copy had dropped the row 23-25 entries. Diff against HEAD is additions only. All eight suites green. Not pushed. Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
Claude Opus 5.5
+53
-4
@@ -8,23 +8,65 @@ at every gate. Started 2026-09-12 during the control board MVP.
|
||||
|
||||
## Open
|
||||
|
||||
- **Inherited Discord engine test intermittency during #1512 review.** Frozen
|
||||
serialized run recorded a tool-turn engine assertion failure and then timed
|
||||
out at 120s. A later full TAP run with a 15s test deadline passed 351/351.
|
||||
Rocko isolated the busy/settled-event test race and missing failure cleanup;
|
||||
Darkwing independently reproduced the event-split assertion. Rocko also reported
|
||||
a timeout-log test race and a separate engine followUp-after-timeout defect.
|
||||
No live incident established. Row21 owner orch-01 notified; no Discord source
|
||||
takeover. Not assumed identical to earlier concurrent hangs.
|
||||
Integration held pending owner disposition; logs and scope in
|
||||
`agents/darkwing/work/relaunch-activity/r1-review.md`. (2026-09-15)
|
||||
Outcome 2026-09-26: 1685deb4 fixed the busy/settled race and the engine no
|
||||
longer sends a follow-up (held prompts). A re-run of the frozen candidate
|
||||
against 21e3e908 passed the serial acceptance command 397/397 three times.
|
||||
Two engine failures remain when tests run concurrently, and they reproduce on
|
||||
clean HEAD without the #1512 files, so they are #1509's (entry below). Sage
|
||||
ruled that #1512 integrates on the serial evidence; it landed in af4203ca.
|
||||
Record: `agents/darkwing/work/relaunch-activity/rerun-2026-09-26.md`.
|
||||
|
||||
- **Discord engine: leaked fake pi on a failed test, and a timeout gap in
|
||||
`busy`.** (a) `engine.test.mjs:100` reads the fake's `commands.jsonl` 20 ms
|
||||
after the second prompt and gets ENOENT under load. The test stops the engine
|
||||
outside `finally`, so the fake pi child outlives it and the test file never
|
||||
exits. Six other tests in the file also stop outside `finally`. This is one
|
||||
confirmed cause of the concurrent hangs in the entry below. (b) In
|
||||
`engine-pi.mjs`, `busy` is `state.busy || pending.some((t) => !t.done)`. If a
|
||||
turn times out before its `agent_start` is read, the turn is marked done while
|
||||
`state.busy` is still false. The next prompt then goes straight to pi, which
|
||||
refuses it ("agent is streaming"). It fails closed, and production timeouts
|
||||
are long enough to make it rare. Seen twice in two default-concurrency runs,
|
||||
and once in three on clean HEAD. Fix in source and tests only; the live
|
||||
connector does not restart for this without Jason's word. Rocko reviews.
|
||||
(2026-09-26, #1509, Darkwing)
|
||||
|
||||
- **Combined concurrent test hangs need isolation.** Row18 R1 frozen six-package runs timed out at 120s/60s, with logs in `/tmp/discord-board-r1-KbMrGQWF/TESTS-first-timeout.txt` and `TESTS-second-timeout.txt`. Serialized R3 independently passes 322/322. Cause and default-concurrency stability remain unverified; investigate separately without changing connector behavior or calling interrupted runs green. (2026-09-14, #1509)
|
||||
|
||||
- **Registration has no "set by" field.** `mosaic seat task` records the
|
||||
task and `updatedAt` but not who set it, so a human session and the
|
||||
orchestrator look the same on the board. One-line record change; rides
|
||||
with the orchestrator assignment piece. (2026-09-12, #1504)
|
||||
- **Usage-limit notice was missed.** Jason reports Rocko exhausted usage without
|
||||
Jason seeing the notice, and is now available again. Investigate where the
|
||||
notice appeared and what operator notification is missing as part of Claude
|
||||
console integration. User-reported, not independently reproduced; no root
|
||||
cause established. Keep outside #1512's relaunch-display scope. (2026-09-15)
|
||||
- **Claude Code seats register but get no board row.** Rocko has no Pi
|
||||
session log, and rows come only from Pi logs. Needs a second row source
|
||||
or a Claude-side log reader. (2026-09-12, darkwing's #1504 report)
|
||||
2026-09-15 #1511 live-test preflight reconfirmed no Rocko row: expected
|
||||
`.pi/state/rocko/sessions` discovery directory absent. Its existing repo
|
||||
registration names dead PID 185602, while the verified native lock owner is
|
||||
3707667. No registration repair, discovery expansion or relaunch performed;
|
||||
test write refused before mutation. Evidence:
|
||||
`agents/darkwing/work/task-attribution/backend-live-verification.json`.
|
||||
- **Fleet seats (`~/.mosaic`) stay on the old launchers.** No registration,
|
||||
no board reply, no `seat task`. Moving them is the stress test and comes
|
||||
after the WebUI and fleet launch work. (Jason, 2026-09-12)
|
||||
- **Sage launcher hook is uncommitted.** `agents/sage/` is untracked; the
|
||||
registration guard was added by hand to match the other four. Commit with
|
||||
the sage directory. (2026-09-12)
|
||||
- **Relaunched seat shows the old last message.** Pi resumes the newest log,
|
||||
so the row's activity stays stale until the first message; only the
|
||||
registration's `startedAt` shows the relaunch. Refinement: "relaunched at
|
||||
X, no messages since". (darkwing, Step 3 log, 2026-09-12)
|
||||
- **Comms skill has no rule for senders without a pane.** The board trailer
|
||||
covers it today; if another pane-less sender appears, put the rule in
|
||||
`skills/ms-communications` instead of a second trailer. (2026-09-12, #1505)
|
||||
@@ -66,6 +108,12 @@ at every gate. Started 2026-09-12 during the control board MVP.
|
||||
nodes. Launch, observe, stop, full transcript navigation, command palette and
|
||||
other screens are absent. Existing palette/appearance switches remain on the
|
||||
single page. Revisit only with a new brief. (2026-09-13 UTC, #1507)
|
||||
- **Ledger counts T3 agent messages as human.** `messageKind` classifies a
|
||||
prompt that opens with the T3 header `[from: x (…) -> to: …]` as human, so
|
||||
the weekly number in Table 2 rises once development runs in T3. Rocko
|
||||
reproduced it read-only, and Filbert confirmed it. The Gate G audit (#1508 R5) does not rely on
|
||||
this count. Fix it before the next weekly number is quoted. (2026-09-26 UTC,
|
||||
#1506)
|
||||
|
||||
## Queue
|
||||
|
||||
@@ -74,3 +122,4 @@ Moved to `docs/plans/QUEUE.md` on 2026-09-13. This file holds only gaps.
|
||||
## Done
|
||||
|
||||
- Ledger (piece 3, #1506): shipped cd0aa5fb, Gate D written 2026-09-12 (18.9 human messages per closed issue).
|
||||
- Relaunched seat shows the old last message (darkwing, Step 3 log, 2026-09-12): closed by #1512 relaunch activity, af4203ca. Filbert authored it; Darkwing and Dewey reviewed. The live board restart and Gate F remain separate.
|
||||
|
||||
Reference in New Issue
Block a user