Commit Graph
2822 Commits
Author SHA1 Message Date
mos 94c414f5fd salvage 2026-11-06: uncommitted work from src/mosaic-stack-rocko-129-r1 (disk cleanup #824) 2026-11-06 10:06:34 -06:00
jason.woltjeandClaude Opus 5.5 70504d23a4 bus, cli, webui: token accounting per run, schema 3h usage_records (row 124, #1618)
Rocko's round 2 candidate e09313aba4d155a1c5af7bfb227ec397e96c0d57444782cd0b48593102bcc684
(38 paths, base 23533625d), approved by Dewey in #1618 comment 28923 (queue rev 1757).
Packet: agents/rocko/work/queue-124/r2/.

- Schema 3g to 3h: packages/bus/src/migrations/3g-3h.sql adds an append-only
  usage_records table; nothing earlier changes. usage_records is in timedTables.
- The transcript usage-source module reads token counts from Pi and Claude
  Code session transcripts and follows no symlink.
- `mosaic usage` in the CLI and a read-only usage section in the Console's
  Settings (one GET route; 400 on a query string).

Decision 123 go: Mos, mos-0737. Activation (3g to 3h) is a migrating run
with Jason present, in Mos's combined re-pin; landing changes nothing live.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 11:08:17 -05:00
jason.woltjeandClaude Opus 5.5 d523272292 sessions: Dewey row 124 round 2 review, approve (comment 28923, rev 1757)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:57:50 -05:00
jason.woltjeandClaude Opus 5.5 7a13129be2 queue: revs 1731-1756, row 124 round 1 changes and round 2 in review (Rocko, Dewey 1738), row 129 claimed (1737), rows 157-161 re-pinned for the I4 checks, D1/D2 re-pinned, row 162 briefed to darkwing, row 164 channel kind added (decision 149)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:54:32 -05:00
jason.woltje cbe071125c logs: Rocko row 124 round 2 (own lines via temporary index) 2026-10-18 10:53:19 -05:00
jason.woltjeandClaude Opus 5.5 810d1a1917 sessions: Sage mos-0716 answers, D1 decision 96 conditions, decision 149 and row 164
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:50:21 -05:00
jason.woltjeandClaude Opus 5.5 c742ecec2e docs: lead decision 149 and the channel kind brief, after row 129 (Q156 item 4, Mos mos-0726, #1661)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:49:07 -05:00
jason.woltjeandClaude Opus 5.5 cd9c071ae6 plans: D1 owner is darkwing
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:45:35 -05:00
jason.woltjeandClaude Opus 5.5 d503552eab plans: D1 brief carries decision 96's four conditions and records the claude pin and Console flags in the pointer (Mos mos-0716, Darkwing survey)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:44:59 -05:00
jason.woltjeandClaude Opus 5.5 23533625d4 sessions: Dewey row 124 round 1 review, changes (comment 28920, rev 1738)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:42:18 -05:00
jason.woltjeandClaude Opus 5.5 e51d8f2042 plans: row 159 I4 tests add the container-address and network-membership checks (Mos, mos-0716)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:42:08 -05:00
jason.woltje 5e0437659b logs: Rocko row 129 design and row 124 count correction (own lines) 2026-10-18 10:39:25 -05:00
jason.woltje 1f3208d4eb logs: Rocko row 124 build and verification (own lines via temp index) 2026-10-18 10:28:43 -05:00
jason.woltjeandClaude Opus 5.5 640f4cef5b sessions: Sage row 155 ruling, D1/D2 rows 162-163, row 154 phase 1 to Mos, queue revs 1722-1730
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:27:35 -05:00
jason.woltjeandClaude Opus 5.5 6a2409f214 queue: revs 1722-1730, row 134 after 155, row 149 round 4 in review (Dewey 1723-1724), D1 and D2 rows 162-163 with P19 notes, row 157 after 163, row 154 brief re-pin
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:27:18 -05:00
jason.woltjeandClaude Opus 5.5 2b5c76eeb4 plans: row 154 brief owns two serve.mjs static routes and round-trips the goals review (Researcher phase 1)
Researcher's phase 1 report needs /editor.js and /editor.css route
entries in serve.mjs, and spec/north-star.md doesn't exist. The brief
now owns those two entries only and names
docs/plans/2026-09-27_goals-review.md for the round-trip test.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:23:35 -05:00
jason.woltjeandClaude Opus 5.5 0df05f2c5c plans: D1 and D2 brief, health-gated stack activate and rollback and the scratch-root rehearsal (#1659, #1660)
Decision 96 D track. D1 turns the de352dfaf window scripts and the
release.sh pointer-and-log shape into stack-release.sh adopt, activate,
rollback and status. D2 adds rehearse on a scratch root with launches
disabled and no model calls. A standing staging stack is left to Jason.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:13:48 -05:00
jason.woltjeandClaude Opus 5.5 e270538675 sessions: Dewey row 149 round 4 in review (revs 1721-1724, comment 28916)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:10:54 -05:00
jason.woltjeandClaude Opus 5.5 7dfda51829 sessions: Sage P19 334-335, queue revs 1713-1721, row 156 brief wake gap, row 149 round 4
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:04:54 -05:00
jason.woltjeandClaude Opus 5.5 9cc0ba0e15 plans: row 156 brief takes Filbert's three edits (task ref in landHolders, land and landing from one read, decision-consumed in flight)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:04:32 -05:00
jason.woltjeandClaude Opus 5.5 957fbfd410 plans: row 156 brief wakes the landing run with a landing turn (Filbert, comment 28913)
A relaunched merge-gate run has land_work but no message to turn on: the
raising run's poll consumes the approval DECISION. The host writes the
instance's landHolders entries into session.json as landing, and the
runner takes one fixed-template turn per entry before its receive loop.
Row 149's chief-of-staff message stays as the fallback; a second land
gets decision-consumed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:03:28 -05:00
jason.woltjeandClaude Opus 5.5 a132b46058 queue: revisions 1713-1720 (rows 124, 154, 155 briefed and 124, 155 re-pinned by Sage; rocko 124 and darkwing 155 claims; filbert row 149 round 3 changes)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:03:16 -05:00
jason.woltjeandClaude Opus 5.5 a3c56343ac sessions: Filbert row 149 r3 review (changes, comment 28913)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 10:00:14 -05:00
jason.woltjeandClaude Opus 5.5 9098c33f7f sessions: Sage row 87 rounds 5-8 and done, row 149 rulings, row 156, I2-I6, row 128 landing
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:52:31 -05:00
jason.woltjeandClaude Opus 5.5 6f85a55189 queue: revisions 1675-1712 (row 87 rounds 5-8 and done, I2-I6 as rows 157-161, row 156 added, row 128 round 1 and done, row 149 round 3 in review)
Other seats' revisions in this sweep: Darkwing 1675, 1680, 1685, 1691,
1699 (row 87 verdicts); Filbert 1678 (row 149 r2), 1681, 1686, 1690,
1701 (row 87), 1702 (row 128 r1); Researcher 1692-1693 (row 128
in-review); Dewey 1709-1711 (row 149 round 3 in review).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:50:42 -05:00
jason.woltjeandClaude Opus 5.5 ade628c8b5 cli: mosaic makes projects and threads and talks in a named thread (row 128, #1622)
Row 128 round 1, Researcher's candidate (agents/researcher/work/queue-128/,
row128.patch, manifest 9eed6a78, 8 paths, base 0f3eb25ea). Filbert
approved round 1 (comment 28895).

`mosaic project create` and `project list` call project.create and
project.list; `init` and `check` keep their arguments and refusals.
`mosaic threads`, `thread create`, `thread open` and `thread read` cover
the thread verbs, and `mosaic talk --thread` sends thread.send as a
REQUEST and prints only the reply to the sent message. `mosaic follow
--thread` is the same loop without the send. A thread reference is its
id, an id prefix of 8 or more characters, or <project>/<name>; unknown,
short and ambiguous references refuse with exit 2 before any send. Every
verb refuses inside an agent run. There is no default thread, so a plain
`talk assistant` still meets thread-required-use-thread-send.
Acceptance 314 step 1 now creates the project and the assistant thread.
New: packages/cli/src/thread.mjs, packages/cli/tests/thread-cli.test.mjs.

Sage's landing gate ran on 77b1a6e8a plus the candidate: 25 steps, all
rc 0 (15 packages, 10 script suites), 14:44:02Z to 14:48:42Z, network
sage-r128_default removed. The commit sits on 7de8b7270, which adds one
docs/SESSIONS.md line that no test reads.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:49:14 -05:00
jason.woltjeandClaude Opus 5.5 7de8b7270a sessions: Dewey row 149 round 3 build, slot runs and review request (comment 28902)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:45:03 -05:00
jason.woltjeandClaude Opus 5.5 77b1a6e8a9 plans: row 87 follow-ups on the start limit, and decisions 147 (B1) and 148 (B2) (#1581)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:41:43 -05:00
jason.woltjeandClaude Opus 5.5 db1519637b sessions: Filbert row 87 r8 and row 128 r1 reviews (approve, comments 28894 and 28895)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:40:24 -05:00
jason.woltjeandClaude Opus 5.5 bb0766826d plans: brief for the host starting the landing run once a merge decision is approved (#1651)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:35:56 -05:00
jason.woltjeandClaude Opus 5.5 917ef55e18 plans: row 87 round 8 counts a stop's no-such-container as gone, bounds each wait per container and gives I6 the unit comment (#1581)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:33:41 -05:00
jason.woltjeandClaude Opus 5.5 3fd0b387f3 sessions: Filbert row 87 r7 review (approve, comment 28889)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:30:59 -05:00
jason.woltjeandClaude Opus 5.5 4c1fee85a5 plans: row 87 round 7 makes the leftover rule wait by id until each core container is gone and names the start order (#1581)
Answers Darkwing's round 6 review (28884) and Filbert's doc-only
follow-up (28883).

- After docker stop, the rule waits for "no such container" by id,
  bounded by the core stop timeout, then rm -f and the same wait; a
  container still there refuses exit 1, which the unit retries.
- A name conflict is now only a hand-made container without the store's
  labels; it stays exit 3, which the unit does not retry.
- Start order: host.lock, store path, rootless check, leftover rule,
  docker run.
- I6 gains two tests: run straight after a stop boots, and a leftover
  never removed refuses exit 1.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:28:56 -05:00
jason.woltjeandClaude Opus 5.5 e1f13a54d2 sessions: Filbert row 87 r6 review (approve, comment 28883)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:25:57 -05:00
jason.woltjeandClaude Opus 5.5 80ebe2afc4 plans: row 87 round 6 gives the store one real-path spelling, starts each core fork on its first line and states the name-conflict refusal (#1581)
Answers Darkwing's round 5 review (28880) and Filbert's doc-only
follow-ups (28881).

- connected follows the channel from the wrapper's creation, as a forked
  child's does; the entry starts the broker on boot and the notifier on
  start, so host.mjs:217 and :244 never wait on a pid line.
- Bus start makes <dataRoot>/bus at 0700 and takes its real path; the
  bind source, mosaic.store label, leftover filter and hostStatus all use
  it.
- A name conflict refuses with exit 3, names the container and the
  client's exit code, gives host.lock back, and removes nothing.
- The host.pids test list names what each test does with the pid.
- I6 gains four lifecycle tests for these.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:23:53 -05:00
jason.woltjeandClaude Opus 5.5 b04014e592 sessions: Filbert row 87 r5 review (approve, comment 28881)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:20:16 -05:00
jason.woltjeandClaude Opus 5.5 75b4af0bcc sessions: Filbert row 149 r2 review (changes, comment 28878)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:17:24 -05:00
jason.woltjeandClaude Opus 5.5 232e054499 plans: row 87 round 5 keys the core container on the store, sets the stop timeout to cover both close waits, and defines connected and host.pids (#1581)
Answers Darkwing's round 4 review (comment 28877) and Filbert's
doc-only follow-up (28876).

- P: the core container's name is mosaic-core-<16 hex of SHA-256 of the
  real path of <dataRoot>/bus>, keyed on the store like writer.lock, so
  two data roots with the same business don't collide.
- Q: close() waits CLOSE_TIMEOUT_MS twice (host.mjs:30, 343, 347). The
  host passes MOSAIC_CLOSE_TIMEOUT_MS to the entry; the core stop
  timeout is two close timeouts plus 5 s (45 s today), used by the
  leftover rule's docker stop -t.
- R: {from, pid} start line; connected turns false on the exit line,
  client stdout close or exit, or a failed stdin write; host.pids is
  null for both forks in containerized mode and adds container; the
  pid-signalling host tests stay local, I6 uses docker exec kill.
- Nit: firstReply (129) and ended (148) cited apart from watchChildren
  (159-165).
- I6 tests and design section 9 add the slow-notifier leftover, two data
  roots, the missing-timeout refusal and connected.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:16:30 -05:00
jason.woltjeandClaude Opus 5.5 bf7d09c6cd sessions: Sage row 87 rounds 3-4, row 128 brief, queue sweep
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:13:22 -05:00
jason.woltjeandClaude Opus 5.5 c95c437cb6 queue: revs 1659-1674, row 87 rounds 3 and 4 (round 4 approved by Filbert), row 128 assigned to Researcher, row 149 round 2
Sage: 1659-1661 (row 87 round 3 to in-review, comment 28868), 1667-1669
(row 128 assigned to researcher, brief re-pinned, briefed), 1671-1673
(row 87 round 4 to in-review on e5dbcf626, comment 28874).

Other seats' revs, swept in by the snapshot: Filbert 1662 (row 87 r3
changes, 28870) and 1674 (row 87 r4 approve, 28876), Dewey 1663, 1665, 1666 (row 149 round 2 in-review, 28872),
Darkwing 1664 (row 87 r3 changes, 28871), Researcher 1670 (row 128
in-progress).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:12:46 -05:00
jason.woltjeandClaude Opus 5.5 125531d5fc sessions: Filbert row 87 r4 review (approve, comment 28876)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:11:37 -05:00
jason.woltjeandClaude Opus 5.5 e5dbcf6264 plans: row 87 round 4 adds the core container's lifecycle and bus status liveness, answering Darkwing's and Filbert's round 3 reviews (#1581)
Design section 3 gains "The core container's lifecycle": the fixed name,
labels and --rm; tagged fork lines that carry each fork's replies, kills
and exit codes, so the host's per-child stop, start-failure kill and
watchChildren keep their logic; what the entry does when one fork exits;
the client ending first; SIGTERM; the host dying without closing stdin
(not spiked, I6 measures it); the leftover removal at bus start; and
bus status liveness from the engine instead of the lock's container pid.
B2 now names caps on the entry's engine-relayed stdout. Section 9 and
I6's files and tests carry the new rules. Broker cites move to
0f3eb25ea after row 143; LAUNCH_OPS is process.mjs:5-20.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:08:45 -05:00
jason.woltjeandClaude Opus 5.5 d5025c8f2e sessions: Dewey row 149 round 2, rebase onto ac55e84fe
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:05:13 -05:00
jason.woltjeandClaude Opus 5.5 0f3eb25ea0 plans: refreshed row 128 brief, the bus project and thread verbs and talk --thread (#1622)
The 2026-10-14 brief predates rows 121, 142 and 143. This one names the
verbs on the existing broker ops, keeps plain talk asking for a thread
with no default, and targets acceptance 314 steps 1 and 3. Owner moves
to researcher.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:03:57 -05:00
jason.woltjeandClaude Opus 5.5 4af594fea0 sessions: Filbert row 87 r3 review (changes, comment 28870)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 09:00:59 -05:00
jason.woltjeandClaude Sonnet 5.5 3e91d528f3 sessions: Researcher row 148 lines of 2026-10-16 (steps 1 and 1b, rounds 1 to 4)
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
2026-10-18 08:59:28 -05:00
jason.woltjeandClaude Sonnet 5.5 2d6681a4d4 sessions: Researcher row 143 build, rounds 1 and 2, landing and worktree removal
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
2026-10-18 08:58:52 -05:00
jason.woltjeandClaude Opus 5.5 ac55e84fe4 plans: row 87 round 3 adds the host channel and keeps bindLaunch, answering Darkwing's and Filbert's round 2 reviews (#1581)
Darkwing L (comment 28863): section 3 gains "The host channel, a
boundary change". The bus host starts the core container with
`docker run -i` as its own child; core-entry.mjs forks process.mjs and
notifier-process.mjs with IPC inside it and relays tagged JSON lines over
the client's stdin and stdout. The core container runs with
--log-driver none, since replies carry caps; I6 tests that. The channel
adds no authentication of its own, so it is boundary change B2.

Darkwing M: the registry keeps the docker run client's pid and
startTime, so bindLaunch, runtime.mjs and broker.mjs are unchanged and
I5 changes no file in packages/bus. The human proof's ancestry check
never meets the client, so the mount list carries that boundary and I5
tests that a session can't reach sock/human or sock/relay. recover()
removes the container, kills a leftover client and binds as today.

Darkwing nits: the start check's temp names are patterns from their
writers, five state files, and the git-socket.mjs split across I3, I5
and I6.

Filbert (comment 28864): section 10 states the Console's outbound
reach on the mosaic-console bridge, no wider than today, with the
--network none forwarder as the not-spiked follow-up named on P19 333.
Section 7 says four networks and lists mosaic-console.

Section 11 lists B1 (the Console bind, before I4) and B2 (the host
channel, before I6); I4's and I6's gates name their ruling.

Doc-only: no test reads either file.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 08:56:57 -05:00
jason.woltjeandClaude Opus 5.5 e1964c854b docs: BUILD-LOG for the row 143 landing; Sage SESSIONS line
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 08:56:31 -05:00
jason.woltjeandClaude Opus 5.5 6e7fdf7ffc queue: revisions 1645-1658 (row 143 done)
Sage: 1645-1646 (re-pins of 143 and 149 to 8fcd0887e), 1650-1651 (row 143 round 2 review request), 1652-1654 (row 87 in-review r2), 1658 (sage-143-done; landed as 0278b9e0b).
Researcher: 1647-1649 (row 143 round 2 in-progress and in-review).
Dewey: 1655 (dewey-143-verdict-2, round 2 approve, comment 28862).
Darkwing: 1656 (darkwing-r87-r2-verdict, row 87 round 2 changes, comment 28863).
Filbert: 1657 (filbert-87-r2, row 87 round 2 changes, comment 28864).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-18 08:55:09 -05:00