feat(agents): Sage launch files, lead text across seat personas, lead decision record

- agents/sage/ launch files committed after Dewey's review (R1 revise, R2
  approve). The launcher test now covers sage with its zai/glm-5.3 high pin.
  The README states the lead role and its limits, and the seat reads but
  never writes the old DYOR records under ~/.mosaic.
- N6 (Dewey authored, Sage reviewed against pins): seat personas and the
  Rocko launcher name Sage as project lead and Darkwing as a collaborating
  engineering seat, per Jason's 2026-09-26 ruling.
- docs/plans/2026-09-26_lead-decisions.md: the push, no merge into next and
  its conditions, the board restart, queue-as-data rulings, Gate F waiting
  on a T3 source, and what stays with Jason.

Launcher tests 6/6 and 1/1, eight suites green. Not pushed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
2026-09-26 15:11:10 -05:00
co-authored by Claude Opus 5.5
parent 42c08d5285
commit d41f81aafe
26 changed files with 849 additions and 42 deletions
+1
View File
@@ -381,3 +381,4 @@ are never rewritten or removed; corrections are new entries.
- 2026-09-26T19:50:06Z | Darkwing (Claude, T3 thread 7525c8e4) | row 6: tree manifest for Sage review, #1512 R1 re-run against 21e3e908 (serial 397/397 x4; default concurrency 395/397 x2 from #1509 engine tests, also on clean HEAD) | reported to Sage over T3, uncommitted, no push
2026-09-26T19:56:50Z | Dewey (T3 Claude Code, thread 84fb346c) | Return-flow and Age candidate R1->R2 | Filbert R1 revise (baseline statement, clear-once test); R2 approved source-only (app.js d1a51646, test a598c0d4, patch c640b601). Webui 9/9. Reported to Sage; integration after #1512 is Sage's. Disclosed two brief in-tree mutation edits to the live-served app.js, since restored. Uncommitted; no push.
2026-09-26T20:02:08Z | Sage (T3 Claude Code, thread 1ef1e4f8) | Records and integration | Local commits 0f5b7cb9 (shared records, BUILD-LOG rebuilt as HEAD plus uncommitted entries, additions only) and 42c08d52 (Dewey return-flow, Filbert R2 approved; BUILD-LOG correction appended for a misdescribed Before line). Eight suites green, webui 9/9. Not pushed. Decision sheet docs/plans/2026-09-26_decisions-for-jason.md written. Darkwing: close #1512, 6a commit go after Filbert, T3 ledger source brief. Dewey: read-only review of agents/sage launch files.
+81
View File
@@ -0,0 +1,81 @@
# Lead decisions, 2026-09-26
Written by Sage (lead). At 20:02Z Jason asked for my decision on the open items
("You are lead... Proactive movement and intelligent decisions"). I read that
as his say-so for the push and the local operational calls below. It does not
cover credentials, the `~/.mosaic` restriction or the live Discord service,
which stay with him. Each item names who decided it and what happened.
## Decided and done
1. **Push `refactor`.** Done at 20:03Z with the jarvis identity:
origin/refactor 43d7574d → 42c08d52 (21e3e908, af4203ca, 0f5b7cb9,
42c08d52). Fast-forward only. All eight suites were green at 42c08d52.
2. **No merge into `next`.** `next` is the old monolith: `apps/`,
Woodpecker CI and the npm packages behind the estate `mosaic` CLI that the
live fleet still runs. `refactor` is 172 commits ahead of it, and `next`
has one commit refactor lacks (2101c9b4, a v1 git-tools fix, #1502). A
merge replaces the default branch's content, may trigger CI and publishing,
and could break the fleet before it is retired. Merge conditions: row 8
(fleet retirement) done, a CI definition for the new root, and 2101c9b4
either carried into `v1/` or ruled moot. Until then `refactor` is the
working branch and pushes stay fast-forward only.
3. **Control board restarted** at 20:03:52Z so #1512's relaunch notice runs
live. Old PID 3414098 (from 09-14) stopped on SIGTERM; new PID 3977979,
log `/tmp/control-board-20260926T200352Z.log`, same flags (none), same
port 7331. Before and after: 44 sessions, identical counts, seen state
kept; `relaunchedAt` now appears in `/api/board`. The WebUI (PID 1266267)
reads files from disk and needed no restart.
## Decided, work under way
4. **Queue as data (#1508).** Section 8 of Filbert's plan is the
specification (sha256 124b6f9e…). Rocko reviews round 3.
- Q1: Gate G reads "run `scripts/mosaic queue next` and do it".
- Q2: Gate G runs on a Pi launcher (`--fresh`); `next` refuses without
an identity.
- Q3: the CLI never commits; the lead commits the queue files by explicit
path after `scripts/test-queue.sh`.
- Q4: D posts only with an explicit per-seat credential file and refuses
the default. It is built and tested against a fake transport.
- J1, J2, J4, J5: as proposed in section 7.2. J6: closes = issues, not
narrowed without a logged reason. J8: E's budget is 12 Gitea calls at
most, 0 with `--no-issues`. Reduced liveness gate: yes. E before D: yes.
- J3 (every row has a brief), J7 (dropped), J9 (row 8 stub): decided
earlier today.
- No separate journal file. The log lives inside `queue.json`, written by
temp file, fsync, rename and a directory fsync. The lock is `link()` of a
complete record, with no automatic reclaim.
5. **Gate F waits for a T3 source.** The ledger's Table 2 reads only Pi
session logs. Filbert confirmed no Pi log carries T3 traffic, so the
Human column cannot see T3 seats. Darkwing briefs a read-only T3 thread
source after the #1509 engine fixes. When it exists, Sage picks Filbert's
Gate F item and Jason sends nothing.
6. **Gate E "all seats"** means every seat that registers on the board. T3
threads are listed as not covered until they carry identity.
7. **Sage launch files.** Dewey reviewed them (revise, small). Sage made the
revisions: `sage` is added to the launcher test, the README is rewritten
for the lead role, and the seat reads but never writes the old DYOR records
under `~/.mosaic`. It creates no new DYOR records until Jason names a
location. Dewey re-reviews, then updates the other seats' persona files
that still name Darkwing as lead.
## Still Jason's
- **Seat tokens for piece D's live round** (credentials). The build does not
wait for them.
- **Discord connector restart** after the #1509 engine fixes. This is a
live service with outside users. Sage asks when Rocko has approved the
fix and the suites pass.
- **Fleet retirement rulings (row 8)**: which seats move or retire, Pi or
T3, how credentials move, and lifting the `~/.mosaic` restriction. See
`2026-09-26_fleet-seats-onto-mosaic-launch.md`.
- **Where DYOR strategy records live**, if that work continues.
- **One live reply test in the WebUI.** 42c08d52 fixes the misleading
pending display. Only a real send shows whether the "no return at all"
report from 09-13 is a second defect.
- **`skills/aws-*`** (23 untracked directories from 2026-09-21, most likely a
plugin install). They stay out of every commit. Moving them out of the
checkout is his call, because they are his files.
- **Row 5 CHAT-02 to 08.** Sage's plan is to proceed under Dewey after the
live reply test. Jason can stop it at any point.
+1 -3
View File
@@ -64,9 +64,6 @@ at every gate. Started 2026-09-12 during the control board MVP.
- **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)
- **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)
@@ -123,3 +120,4 @@ Moved to `docs/plans/QUEUE.md` on 2026-09-13. This file holds only gaps.
- 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.
- Sage launcher hook uncommitted (2026-09-12): closed by the agents/sage launch files commit, Dewey review R1 revise, R2 approve (`agents/dewey/work/sage-launch-review-2026-09-26.md`), launcher test now covers sage.