Commit Graph
1441 Commits
Author SHA1 Message Date
jason.woltjeandClaude Opus 5.5 814426c6eb docs(sessions): Sage lands row 45
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:29:13 -05:00
jason.woltje f345ae851f queue: rev 219, row 45 done (#1527, candidate 5b067a9d landed as 9cdb6d82) 2026-10-09 09:28:24 -05:00
jason.woltjeandClaude Opus 5.5 5c680166df docs(build-log): row 45 landed; Rocko's round 1 and 2 entries and SESSIONS line
Rocko's three BUILD-LOG entries (row 45 started, round 1 ready, round 2
ready) and their round 2 SESSIONS line, plus my landing entry with the
gate counts and the reviewers' non-blocking follow-ups.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:27:54 -05:00
jason.woltjeandClaude Opus 5.5 2be51cf5b1 chore(sage): drop my trackers-boot copy, landed in packages/cli/tests (row 45)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:27:34 -05:00
jason.woltjeandClaude Opus 5.5 9cdb6d82e3 feat(cli): S4 follow-up, refusal backoff and tracker boot (row 45, #1527)
Rocko's round 2 candidate, packet agents/rocko/work/s4-follow-up/
(build.patch c8cec070, candidate manifest 5b067a9d, 8/8 OK).

- Definite DM refusals wait the full 30-minute cap, counted from the
  journal's last refusal, so five refusals span about two hours before
  gave-up (lead decision 73). Unknown outcomes keep doubling.
- Broker close sends at host.mjs:144/150/184/188 pass a callback, which
  closes the EPIPE window both reviewers found in round 1.
- README documents manual recovery for an open decision.
- trackers-boot test, X9, X14, and Darkwing's round 1 notes 1-4.
- The append type check stays out; Rocko's reason holds (both reviewers
  agree).

Reviews: Darkwing approve (comment 26884), Filbert approve (26886).
Landing gate on b13fef4c plus the patch: every node suite and every
scripts/test-*.sh green, test-task 98/0.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:27:34 -05:00
jason.woltjeandClaude Opus 5.5 f4714aa03b docs(sessions): Filbert row 45 round 2 review
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:26:32 -05:00
jason.woltjeandClaude Opus 5.5 9b067be173 docs(review): row 45 round 2 review record, approve (filbert)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:26:24 -05:00
jason.woltjeandClaude Opus 5.5 5eb9fa8ae7 queue: rev 218, row 45 round 2 approve by filbert on #1527 (comment 26886, candidate 5b067a9d)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:26:19 -05:00
jason.woltjeandClaude Opus 5.5 b13fef4c28 docs(review): row 45 round 2 review record, approve (darkwing)
Comment 26884 on #1527, candidate 5b067a9d, queue rev 217.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:20:38 -05:00
jason.woltjeandClaude Opus 5.5 354fa9f6bb queue: rev 217, row 45 round 2 approve by darkwing on #1527 (comment 26884, candidate 5b067a9d)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:20:34 -05:00
jason.woltje 19dcc5531d queue: rev 216, row 45 in review round 2 on #1527 (request posted by sage, comment 26882); includes revs 212-214 (rocko: in-progress, in-review round 2, candidate 5b067a9d) and rev 215 (request) 2026-10-09 09:11:22 -05:00
jason.woltjeandClaude Opus 5.5 af1377d7e8 docs(cli): row 45 S4 follow-up round 2 candidate packet (rocko)
build.patch c8cec070…6756, candidate-manifest 5b067a9d…0e0e, base d539d8d2.
Covers Darkwing 26872, Filbert 26880 and lead decision 73.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 09:10:55 -05:00
jason.woltjeandClaude Opus 5.5 d539d8d2cc docs(sessions): Filbert row 45 round 1 review
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:32:43 -05:00
jason.woltjeandClaude Opus 5.5 8bcdd9a6f8 docs: SESSIONS, Dewey row 46 review and Sage network cleanup, row 46 landing, row 45 rulings
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:32:43 -05:00
jason.woltjeandClaude Opus 5.5 46baf3f854 docs(review): row 45 round 1 review record, changes (filbert)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:32:38 -05:00
jason.woltjeandClaude Opus 5.5 6e4af4b7c2 queue: rev 211, row 45 round 1 changes (filbert)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:32:35 -05:00
jason.woltjeandClaude Opus 5.5 a690f09132 docs(plans): lead decision 73, row 45 round 1 rulings (definite refusals wait the full cap; close send callback)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:31:23 -05:00
jason.woltje 1aad1e09ee queue: rev 210, row 46 done (sage, landed 2d308abd); includes rev 208, row 45 changes from darkwing (comment 26872), and rev 209, row 46 approve from dewey (comment 26873) 2026-10-09 08:30:36 -05:00
jason.woltjeandClaude Opus 5.5 2d308abd16 test(conversation): fake-pi tool child signals ready after its TERM handler (row 46, #1528)
Fixes the K1, K3 and K10 race: a child could get SIGTERM before it
installed its handler. Author: Darkwing. Reviewer: Dewey (approve,
comment 26873). BUILD-LOG landing entry with gate counts and the
correction to decision 72's probe claim.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:30:01 -05:00
jason.woltjeandClaude Opus 5.5 1a481a1f4d docs(cli): row 45 round 1 review, changes on #1527 (darkwing)
R1: the guarded close send at host.mjs:144 and :150 can still fail with
EPIPE after a broker SIGKILL; reproduced, fix is a send callback.
R2: give-up lands 7.5 min after the first refusal, against decision 72's
reason; Sage's ruling.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:29:50 -05:00
jason.woltjeandClaude Opus 5.5 9e172fb494 queue: rev 208, row 45 round 1 changes by darkwing on #1527 (comment 26872)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:29:41 -05:00
jason.woltjeandClaude Opus 5.5 e52493f7ae docs: BUILD-LOG, Docker network removal result (17 removed, 32 to 15)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:26:29 -05:00
jason.woltjeandClaude Opus 5.5 7525431978 docs: BUILD-LOG, unused Docker networks listed before removal (Mos's ruling)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:26:07 -05:00
jason.woltje 112071c74b queue: rev 207, row 45 in review round 1 on #1527 (rocko; request posted by sage, comment 26869) 2026-10-09 08:16:10 -05:00
jason.woltjeandClaude Opus 5.5 156eb07add docs(cli): row 45 S4 follow-up candidate packet (rocko)
Packet for #1527, base 521597bb: build.patch, candidate manifest
b329fdcb, packet manifest, BUILD.md, gate and mutant receipts. The
candidate itself is not committed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:15:47 -05:00
jason.woltjeandClaude Opus 5.5 7478ee2c02 docs(conversation): row 46 cohort K1/K3/K10 diagnosis, receipts and candidate packet (darkwing)
The ignoreTerm tool child was TERMed before Node installed its handler
when the claim store sits on a fast disk. Candidate fixes the fixture;
the patch itself is not committed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:11:48 -05:00
jason.woltjeandClaude Opus 5.5 76506c7e96 queue: rev 203, row 46 in review round 1 on #1528 (darkwing); includes rev 201, row 45 in progress (rocko)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 08:11:43 -05:00
jason.woltjeandClaude Opus 5.5 521597bbe0 queue: rev 200, row 46 in progress (darkwing)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:56:57 -05:00
jason.woltjeandClaude Opus 5.5 41c5a8563f docs: SESSIONS, Sage lands rows 38 and 39 and opens rows 45 and 46
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:55:50 -05:00
jason.woltje d0c20a2f24 queue: rev 199, rows 45 and 46 added and briefed (sage, decision 72) 2026-10-09 07:55:41 -05:00
jason.woltjeandClaude Opus 5.5 ec2a2c6773 docs: lead decision 72, the S4 follow-up and cohort briefs, and the trackers boot test
Decision 72 rules on F2 (five definite refusals stop a DM; unknown
outcomes keep retrying) and J4 (type-check confirmed journal lines),
and opens two rows: the S4 follow-up for Rocko and the K1, K3 and K10
cohort failures for Darkwing. The trackers boot test from the row 39
gate is kept under agents/sage/work/s4-follow-up/ until the follow-up
moves it into packages/cli/tests/.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:54:52 -05:00
jason.woltjeandClaude Opus 5.5 e580ee2239 queue: rev 195, row 39 S4 done (sage, 2f5303c1)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:50:18 -05:00
jason.woltjeandClaude Opus 5.5 a78f64b1cf docs: BUILD-LOG, S4 round 1 and round 2 entries, the M28 correction and the row 39 landing
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:49:52 -05:00
jason.woltjeandClaude Opus 5.5 2f5303c1c7 feat(cli): the mosaic CLI, broker host and decision notifier (row 39, S4, rocko)
packages/cli adds mosaic inbox, decide, tasks, agents and trail over the
human-cli transport, and mosaic bus start, stop and status as the trusted
host (unit mosaic-bus@<business>, scripts/bus-service.sh). The host boots
packages/bus/src/process.mjs, passes config.trackers from the tracker.*
variables (lead decision 70), and runs a notifier child. The notifier DMs
each open blocking decision once and sends an 08:00 America/Chicago
digest, journaled in notify/<business>/sent.jsonl at 0600 with no Discord
ids. A torn journal tail is copied aside and truncated; a malformed line,
a directory looser than 0700 or a symlinked journal refuses (lead
decision 71). packages/discord gains dmRecipient, createDm and notify.mjs.

Candidate agents/rocko/work/slice1-s4, base b9b6cf00, build.patch
b52f7d68, manifest e858504e (29 files). Darkwing approved round 2 on
#1521 (comment 26855), Filbert approved round 2 (comment 26856). The
packet's mutant table lists M28 as killed; it survived, and BUILD-LOG
records the correction.

Integration gate in a worktree on 2557e29d with the patch applied:
bus 67, business 60, cli 49, control-board 124, discord 178, ledger 78,
mosaic 69, queue 148, seat 19, tasks 51 and webui 14, all with no
failures. Conversation is 149/3, the same K1, K3 and K10 cases that fail
on the base; S4 doesn't touch the package. Every scripts/test-*.sh is
green, with test-release 14/14 and test-task 98/98 on the existing gate2
compose network. A scratch test, not in this commit, booted the real
host with trackers against S3's fake Vikunja: the adapter went ready and
a task.close on a missing task answered task-not-found after a Vikunja
read.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:49:38 -05:00
jason.woltjeandClaude Opus 5.5 2557e29dc7 queue: rev 194, row 38 S3 done (sage, 7e73c2cd)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:41:46 -05:00
jason.woltjeandClaude Opus 5.5 ffd3a9d86c docs: BUILD-LOG, S2, S2b, S2c and S3 entries and the row 38 landing
The seats' uncommitted S2 to S3 entries land with row 38. Rocko's two S4
entries stay uncommitted until row 39 lands.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:41:17 -05:00
jason.woltjeandClaude Opus 5.5 7e73c2cd13 feat(tasks): the Vikunja v2 adapter, broker task verbs and sync (row 38, S3, darkwing)
packages/tasks adds the Vikunja v2 client, the eight task verbs, the
board-plus-cursor poll with its 60 s window and the digest. The broker
gains the task verbs and boots trackers from the boot config (lead
decisions 66 to 68). Due dates are truncated to the second and recorded
as truncated (B1). A write that lands but whose final read fails counts
as landed, in update and in create (B2).

Candidate agents/darkwing/work/slice1-s3, build-r2.patch 71ce87e6,
manifest e10e30e3 (28 files). Filbert approved round 2 on #1520
(comment 26853). Darkwing's post-reset rerun: test-release 14/14,
test-task 98/98 (comment 26857).

Integration gate in a worktree on c4baf779 with the patch applied:
bus 67, business 60, control-board 124, discord 173, ledger 78,
mosaic 69, queue 148, seat 19, tasks 51 and webui 14, all with no
failures. Conversation is 149/3. The three cohort kill cases (K1, K3,
K10) fail the same on the unpatched base, and the patch doesn't touch
the package. Every scripts/test-*.sh is green. test-release 14/14 and
test-task 98/98 ran on the existing gate2 compose network, because the
host's Docker address pools are exhausted. No network was created or
pruned.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:40:48 -05:00
jason.woltjeandClaude Opus 5.5 c4baf77916 docs(slice1): row 38 S3 round 2 gate rerun, test-release 14/14 and test-task 98/98
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-09 07:33:26 -05:00
jason.woltjeandClaude Opus 5.5 f5eb85ea4e docs: sessions, filbert row 39 S4 round 2 review
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 20:16:29 -05:00
jason.woltjeandClaude Opus 5.5 2de56a471c docs(slice1): filbert row 39 S4 round 2 review record (approve)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 20:16:18 -05:00
jason.woltjeandClaude Opus 5.5 1608e3da45 queue: rev 193, row 39 round 2 approve (filbert)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 20:16:12 -05:00
jason.woltjeandClaude Opus 5.5 9bdee45517 queue: rev 192, row 39 round 2 darkwing approves (comment 26855)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 20:01:45 -05:00
jason.woltjeandClaude Opus 5.5 3c18473d11 docs(slice1): darkwing row 39 S4 round 2 review record (approve)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 20:01:06 -05:00
jason.woltjeandClaude Opus 5.5 26bd829c1d queue: revs 188-191, row 39 round 2 in review (rocko moves, sage request)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:56:02 -05:00
jason.woltjeandClaude Opus 5.5 fdbb4e34c4 docs: sessions, filbert row 38 S3 round 2 review
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:41:41 -05:00
jason.woltjeandClaude Opus 5.5 d5c95244c8 docs(slice1): filbert row 38 S3 round 2 review record (approve)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:41:32 -05:00
jason.woltjeandClaude Opus 5.5 5d55cfc156 queue: rev 187, row 38 round 2 approve (filbert)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:41:27 -05:00
jason.woltjeandClaude Opus 5.5 bb267da534 queue: rev 186, row 38 round 2 in review (darkwing)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:28:10 -05:00
jason.woltjeandClaude Opus 5.5 b144a03d47 docs(slice1): darkwing row 38 S3 round 2 packet
B1 truncates due dates to the second; B2 records what landed when the
final read fails; tests for V9, V21 and S5. Candidate manifest
e10e30e3, 28 files over c9ef7ee4. Mutants 46/63. Live provider cases
in test-release and test-task failed on a zai usage limit (429).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:27:17 -05:00
jason.woltjeandClaude Opus 5.5 c9ef7ee49f queue: rev 184, row 38 back to in-progress for round 2 (sage)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-08 19:06:44 -05:00