Lifecycle Task 2 (#797). A confirmed new-project selection now becomes a
usable product: the code checkout, the organization mapping, the records
repository with the original intent as the owner's spec commit, the chat
association and the working repository, each journaled as its own receipt
(bootstrap:<plan_digest>:<step>) and recoverable after a kill.
- business: addProject is a private exact-add writer under the existing
organization lock and receipt discipline; hold runs a synchronous check
under that lock; findAddition recovers a prepared receipt. Ordinary
writers still refuse every project change.
- bus: prepareBootstrap and executeBootstrap; activateManagedProject
reloads only a receipt-backed additive root and admits it to the broker
after readiness; request.admission host IPC op for the launcher.
- #800: the bound organization revision and association are re-verified
inside the organization lock at the start of execution; a mismatch
records request-plan-stale and performs no effect.
- cli: trackerFor skips reserved products; the launcher refuses to clone a
product the bus has not admitted.
- seat: initializeWorking seeds the working repository, host-only, with no
work ref or push authority.
- schema: append-only migration 3o to 3p widens the request_events kind
list with bootstrap.stale and bootstrap.completed.
Route selection moves into one helper, pickRoute(proxyOf), that both checks call: the
primary preflight, and the fallback with its own preflight only when the primary's
fails, with the same messages. The final check passes proxyFor and is otherwise
unchanged. The first check of a proxy launch passes a stand-in session proxy (marker
key PENDING_ADMISSION_KEY and the configured loopback base URL), which reaches only
the preflights, then runs gate() with a null session proxy on the predicted route only.
The round 1 union over both routes is gone.
The managed fixture takes extra (more harnesses switched on), real (harnesses loaded
unfaked) and hostEnv. Seven tests in proxy-launch-order.test.mjs.
F1: with system.proxy set, the first launcher check no longer returns
before the account, sandbox, capacity and limit checks. It skips only the
harness preflight and the session proxy key match, which need the key P2
admits in startLocked. A launch that can never start now refuses before
authorizeLaunch, the workspace and checkouts, and modelPreflight. The first
proxy pass accepts only credential "proxy" for a declared account, tries
the fallback model when the primary refuses, and lets mayLaunch
key-quota-no-model-key through so P2 can issue the first key. The final
check is unchanged and still runs before newRun and spawn.
F4: the proxy test option is renamed testProxy and createLauncher throws
test-proxy-refused when it is given with system.proxy.
launch-account.test.mjs is a second caller, so the option stays.
Tests: proxy-launch-order.test.mjs (6), launcher.test.mjs F4 throw test;
the managed launch fixture gains bwrap, admit and trace.ops.
Source-candidate: poe d9a564e6d20f5f0fd75ce45b12cbbf8bb4c9d568\nSource-candidate: magica38ba5762b06716db1dee00d0afec162656488f5c\nValidated321whole-file phase plus whole bus1349/model-proxy100/webui490; final gate tooling checks pending, not landed.
Preserve the draft for inspection under sage-3113. Tests and mutants have not run. Old-test adaptations approved in mos-1316 and mos-1317 are recorded in OLD-TEST-CHANGES.md.
The section "recover() change, for a design read" covers three things, with
file:line against aca16404c. Every leftover is still bound and ended as
host-lost, and a survivor only refuses legacy-run-live while it lives. The
5 s wait applies only in the bwrap kill branch. No old test's expected value
changes. The fallback is to revert to the base recover() and leave the
refusal untested. The survivor log line now names the outer and runner pids
so an operator can clear it, and the new test's log assertion matches.
recover() kept a survivor only when a bwrap outer pid outlived SIGKILL, so
the Q2 refusal (BUILD.md:177-179, t1-sessions.md:109) had no test. A leftover
whose runner still ran after its outer pid was gone was ended and dropped.
Now recover() waits on the outer pid and the runner, keeps any leftover where
either still runs, and logs that it still runs. check() reads only the
survivors that still run.
session-launch.test.mjs adds a test where a sessionless leftover's runner is
a sleep child and its outer pid is gone. It asserts the legacy-run-live
refusal with no launch and no session workspace, then one launch once the
child exits. BUILD.md adds mutants M10-M12 and replaces the "no test" note.
threadsState gives one row per session with `session` and `legacy`; threadIdle
idles a run against its bound session. Each session gets its own store
(threads/<b>/<t>/sessions/<s>/, or the thread's old store for a legacy-3l
session) and its own workspace (session-workspaces/<b>/<i>/<s>/), held by an
O_EXCL <ws>.lock from before the clones to the run's proven exit. A legacy
session's workspace binds in-sandbox at the old instance path. sessions.json
is v2 and reads v1. New tests: cli session-launch.test.mjs, seat
session-workspace.test.mjs. Not yet run: tests wait for Sage's CLEAR.
Two old assertions change as exact updates:
- mos-1285: end-launch.test.mjs threadsState deepEqual. The old row shape was
{ thread: 'th-1', instance: 'coder', pending: 0, unread: 0, lastMessage: null,
lastOpen: '2026-10-15T00:00:01.000Z', lastClaim: null, holder: null }; the
row keeps every key and value and adds session: 'th-1', legacy: true.
- mos-1289: thread-launch.test.mjs:182, old line
`const store = join(f.dataRoot, "threads", "acme", A);`
now reads A's default session id from threadsState's `session` key; :183-185
unchanged; one added assert that threads/acme/<A>/session is absent.
Unify halt and fire cancellation by verified run identity with durable first-owner receipts and shared deadlines. Integrate the instance control with the current host, library and tester-socket paths. Focused nine-file evidence is 62 passing tests; broad suites, mutants and review remain pending.
The business file accepts a kind "library" project entry, and each consumer
that assumed a project root skips it. An organization write whose projects
differ from the file's is refused (M9). The bare mirror is created at the
projectRepo path with no remote. library.file and library.status are human
only and refuse an agent session with human-required.
Candidate herb/row215-on197 dde3445ab on a36523713, Filbert APPROVE rev 2924.
Lands Morgana's round 4 candidate, 2b3e67e36 (base c771a36f4, branch morgana/row213-r4), approved by Webby
(webby-0071, REVIEW-r4 02bb0afb3, rev 2775). Manifest digest 26d4d0ecff56, 35 paths, plus Morgana's
four packet files under agents/morgana/work/queue-213/ (base.txt, BUILD.md, candidate-manifest.sha256,
mutants.py): 39 paths, blobs and modes from the candidate. No 213 path changed between c771a36f4 and
this commit's parent. Patch-id f313e69b6f7e, the same as c771a36f4..2b3e67e36.
Evidence: Morgana's slot run on 2b3e67e36 (sage-1844): singles 191/0 and 31/31 mutants killed.
Gate on my slot (sage-r195land, base 38b83ea5c plus 195's 5 and 213's 39 paths, 09:45:52-09:57:52Z): business 200/0, bus 542/0, harness 140/0, cli 663/0; scripts auth 15/0, conductor 17/0, config 31/0, discord 78/0, extension-package 18/0, foundation 44/0, land-work 86/0, queue 156/0 plus 28/0, release 14/0, task 98/0; the models mutant L1 killed (launch-settings 15/1), restore matched.
Between the gate base 38b83ea5c and 4364dddb0 only docs/plans/2026-10-20_host-credentials.md changed (01e1fe512, 4364dddb0), which no test reads. Row 195 landed as this commit's parent; it shares no path with 213.
Webby's N2 (a host grant for a creative role) is a row 235 acceptance item (mos-1163), not a deferral.
Squash of Megavolt's 627979a17..86963d281 on origin/megavolt/row199-on-190
(base 00d4cc1f6, row 190's landing), the 37 manifest paths, build.patch
05383075, manifest 35f900fd (Duckworth approve round 1, comment 29779,
rev 2540). Mutant batches 1 and 2 in agents/megavolt/work/queue-199/BUILD.md:
batch 2 26 of 28 killed, M17 and M27 equivalent. docs/TOOLS.md is a 3-way
merge with row 200 (9e1085816): row 199's hunk applies unchanged (patch-id
d88379111e2e) and no test reads the file. Gate on 9e1085816 plus the patch:
15 package suites 2735 pass 0 fail, 10 scripts/test-*.sh suites 429 pass
0 fail (plus 156 node tests in the queue suite). Refactor moved to 76134dfde
since, a brief touching no manifest path. No live change: the stack runs from
copy 4429a104f until the 10-24 re-pin window.
Author and gate owner: Sage (mos-0855).
Role files take an optional skills list. The bundle reads each named skill
from <dataRoot>/skills-enabled, copies it into the bundle and renders every
file into prompt.md between skill-file markers, so the prompt text matches
the bundle copy byte for byte. The role's skills together are capped at
SKILL_BYTES (64 KiB): the claude adapter passes prompt.md as one argument,
and Linux caps one argument at 128 KiB. Symlinks are refused, not followed.
The launcher checks the list before a run exists: skill-not-enabled names
the activate command, anything else refuses skill-refused.
Pi keeps --no-skills; Claude Code keeps --disable-slash-commands and
--restricted. The two harness modules and MOSAIC_SKILLS are unchanged.
First lists: coder, reviewer, cto and pm, ms-unslop on each.
Adds the harness plug-in kind (interface 1). packages/plugins/harness/pi
and claude-code hold what core branched on: the adapter, thinking levels,
preflight, version probe, sandbox mounts, builtins line, typed tool names,
gate timeout, bundle files, adapter env, turn end and session-files path.
Core reaches a module only through the loader.
A session's route is the instance's harness, model and thinking vars, or
the three fallback. vars; a missing one refuses no-route, and the system
file's execution keys are never read for a session. The launcher checks
the primary route, then the fallback: harness-off, harness-refused,
thinking-unsupported, then preflight. A failed preflight falls back when
a fallback is set, and any refusal of the fallback names the primary's
failure too. Account checks run
only when the route's module counts an account. The manifest records
route, routeReason and harnessVersion, replacing piVersion and
claudeVersion. pi gets --thinking, Claude Code --effort, both from
MOSAIC_THINKING.
The business file refuses a partial fallback. routes and routes.set are
human-only bus verbs outside ORGANIZATION_KEYS; checkRoutes is shared by
routes.set, instances.set and limits.set and checks only changed routes.
The chief of staff changes an instance's model, and the assistant's whole
vars (Q169), through limits.set, so its route write runs the same checks.
A model outside launch.models refuses unknown-model, primary or fallback,
and routes.set passes that code through.
A new run binds only on a switched-on harness module name and records
its transcript path, which the usage reader uses. Settings gains a
Routing table with six selects per instance and loses the Role models
fieldset; it posts changed rows to /api/routes. webui/src/bus.mjs is
unchanged.
Until Jason's `mosaic plugins set` adds "harness": ["claude-code"], a new
launch refuses harness-off.
The business file can name the account claude-code launches use,
`launch.account` = {name, credential}. `name` is an identifier and
`credential` names one login set's environment variables, never a value.
`launch.limits.tokens.daily.<account>` = {limit, since, reset, timeZone}
sets a daily quota for that account. A daily key that isn't the account's
name refuses the business read.
The new plug-in limit-check/daily-quota (interface 2, pure) starts a day at
the first instant at or after `reset` on that local date in `timeZone`. Across
DST that makes a 23- or 25-hour day, and a reset in a skipped hour starts at
the gap's end. It counts the account's known records of all four kinds since
the later of the day start and `since`, and counts unknown turns apart.
The launcher refuses account-credential-missing, account-credential-ambiguous
and account-is-credential (an account name equal to a session credential's
value). Messages name variables, never values. The account rides mayLaunch,
bindLaunch, the usage records, mustStop and the launch record. A pi launch
has no account, records NULL, and no daily quota covers it. `mosaic limits`
and the Console's Settings show one fixed line when a daily row shows:
"Daily quotas count only this stack's own use of the account, not its use
anywhere else."
Bus schema 3h to 3i: 3h reserved usage_records.account as
CHECK (account IS NULL). The new step 3h-3i.sql rebuilds the table in one
transaction, keeping every row's seq and the sqlite_sequence value, and
recreates the three append-only triggers. All of sqlite_master equals 3h's
apart from the account line. A 3h engine refuses a 3i store.
packages/bus/tests/account-migration.test.mjs covers all three, with a
step that fails partway and leaves 3h intact. 3i goes live only through
`stack-release.sh activate ... --migrate` with Jason present (P19 371); the
activate path takes the pre-migrate backup, and the way back is restoring
it (agents/dewey/work/queue-126/MIGRATION.md).
Mos's go mos-0835, six conditions: (1) one transaction, account-migration
test 2 and mutant D29; (2) sqlite_master against 3h, test 1 and mutant D28;
(3) account is never a credential, the launcher's account-is-credential
refusal (launch-account.test.mjs) and the business name pattern
(token-limit-settings.test.mjs); (4) MIGRATION.md, accepted by Mos in
mos-0837; (5) the packet's DESIGN.md "no schema change" line corrected;
(6) the public/ digest below.
The public/ change in bus.js (the daily line under the token-limit table)
carries Mos's decision 123 go mos-0833 on the +/- digest 03e6d9da...ba78,
unchanged at landing.
Owner Dewey, brief docs/plans/2026-10-14_prd-1.2-build.md, "Daily quota for
the credential the stack uses today". Review round 2 rebases the round 4
build onto 1df04f52f (row 167). Reviewer: Filbert approve 29068 on round 1
(manifest d18314f7...8e65); Filbert approve 29080 on
round 2 (manifest f332db76...6fa6).
Seat run on round 2: touched 158/0, singles 1388/0 with 1 esbuild skip,
test-land-work.sh 86/0, 30/30 mutants killed.
Sage gate on 54319f552: GATE_PASSED, 2474+422/0, all 15 packages, the queue
suite and 10 script selftests.
Nothing live.
Until now a landing ran only when the chief of staff or merge-gate
followed row 149's manual steps. The host now does it.
Broker. landHolders(business) lists the approved merge decisions each
instance holds, sharing the #held generator with landHeld.
landRelease(record) releases a run's claim with by='land-relaunch'.
Delivered and unread messages keep the run, and a run that hasn't had
its first message.receive answers {released:false, landing:true}
(#received, round 2), so a landing turn in progress is never cut. A
run that never reaches its first receive, a hung landing turn or a
broker restart, keeps the release closed, and the decision falls back
to row 149's path.
usage.begin accepts a decision id that landHolders lists for the run.
The bus process answers both ops from their own launchOp lines and
refuses any op it doesn't name.
Launcher. start() reads landHolders once for a non-thread instance and
takes land_work and the session's landing list from that one answer.
landPass() runs after threadPass() on each tick.
Runner. One turn per landing entry before the message loop, with a
usage bracket on the decision id.
Docs. A "Landing runs" section in the cli README and docs/TOOLS.md.
roles/merge-gate.md, cto.md and chief-of-staff.md say the host starts
the run, and row 149's steps are the fallback.
Owner Dewey, brief docs/plans/2026-10-18_landing-run-launch.md, design
DESIGN.md in the packet (sage-0808). Round 2 answers Filbert's F1-F3
(29033, rulings sage-0942). Reviewer on candidate manifest
72a5c1b6...b700: Filbert approve 29039. Seat run 4: 290/290 singles,
36/36 mutants killed. Sage gate on a618528b2 (candidate 524bfcc80): GATE_PASSED 25/25. Package tests 2258 plus queue 156, script selftests 422, 23:30:07Z to 23:38:04Z. Run 1 stopped at pkg-webui on board-held.test.mjs:163, the P19 366 timeout, 220/1. Run 2 resumed at pkg-webui on the same tree: webui 221/0 and every scripts/test-*.sh green.
Nothing live.
Adds token limits under launch.limits.tokens (instances, providers, keys,
models.P.M). Core (packages/bus/src/limits.mjs) reads the organization
file and the per-turn usage records row 124 writes, then asks every
switched-on limit-check plug-in; the first refusal wins. A limit no
switched-on check reports reads "not enforced". The limit-check kind is
interface 2 (mayLaunch, mustStop, report); a v1 check is refused at load.
The shipped token-limit check is pure and counts known end records only;
unknown turns add nothing and are shown as their own count.
The launcher refuses limit-reached through the host's mayLaunch op, or
limit-check-failed naming the check. The broker asks mustStop after a
usage end and stops the run at its next receive or state. Settings stamps
since on a new or changed limit and runs reset; launch.mjs and
business.mjs validate the shape. Readers: mosaic limits and mosaic limits
reset, the bus limits view, the Console /api/bus/limits route and the
Settings token table with Reset. Key limits stay "not enforced" until
row 126 names accounts on records.
Owner Dewey, design under lead decision 150.
Reviewer Filbert: r1 changes (comment 28965), r2 approve (28981), r3
approve (28996) on candidate manifest 8b71c405...fe56 after the rebase
onto row 164 (37 of 38 paths with identical +/- lines, TOOLS.md:621
bracket). Decision 123 go on the bus.js hunk from Mos (mos-0814). Sage
gate on b6827d19e: 25 steps, all rc 0 (15 packages, 10 script suites), 2295 node tests and 422 script selftests, 0 failed, 20:03:25Z to 20:08:08Z, network sage-r125_default removed.
Live stays as pinned. Not part of the 8e7ea89a1 window.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
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]>
Row 137 round 4, Darkwing's candidate (agents/darkwing/work/queue-137/r4/,
build.patch 0cabe175, manifest 548ee477, 31 paths, base 63c82f1c4).
Filbert approved round 4 (comment 28809) and Dewey approved it (28816)
after round 3 changes (28801, 28805). Darkwing's round 4 ran 9/9 mutant
kills, bus 317, seat 150, land-work 86.
Round 5 is a rebase only (agents/sage/work/queue-137-r5/, build.patch
d6cbaaa8, manifest f73598fe). Row 150 changed docs/TOOLS.md, broker.mjs
and cli/README.md under it. The round 4 patch applied unchanged onto
435d1c616, and with index and @@ lines removed the two patches are
byte-identical. Filbert checked the interdiff (comment 28818).
A landing moves refs/heads/main in <dataRoot>/working/<business>/
<project>.git, never the project root or canonical refactor. The seed now
fetches the root as refs/heads/root and fast-forwards main only when it
is an ancestor, so a landed main survives the next push. Only a
cross-role merge decision lands. Its squash names the real channel:
"via the CLI" for the human, and "as its arbiter, via the broker" for an
arbiter's decision.resolve. Every other class refuses not-authorized
before the human check.
This carries row 139's two items. REQ-LAND-1: a gated merge decision
never lands. REQ-DEC-2: the host land op accepts an arbiter-resolved
merge. land-work's read.mjs stays human-only, and land-work.sh still
accepts only a human CLI resolution.
Sage's landing gate ran on 435d1c616 plus the candidate: 25 steps,
all rc 0 (15 packages, 10 script suites), 20:51:00Z to 20:55:34Z,
network sage-r137_default removed. Cherry-picked onto 5d98fb194, which
added only a docs/SESSIONS.md line.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Darkwing's row 121 round 2 (agents/darkwing/work/queue-121/r2, base
20d2b5788, manifest 710d5086...e67e9b, 30 files), applied unchanged on
d7ebaa9a5; no commit since the base touches any of the 30 paths. Dewey
asked for changes on round 1 in comment 28591 (F1 to F6) and approved
round 2 in 28615. Landing gate on d7ebaa9a5 plus the candidate: all 24
suites passed, 0 failed.
F6 and Dewey's three round 2 notes are follow-ups (sage-0369, P19 task
311). One of them corrects the packet: BUILD.md says the decision-route
setup's projects key is needed, and Dewey's probe showed project.create
reads it only with repo, so the key is dead setup.
The live bus stays at 3b until Mos's schema window migrates it.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
launch.max becomes launch.models plus launch.limits (total, providers,
exact provider/model). The launcher re-reads limits on every attempt.
Settings and `mosaic limits` write through one locked, journaled
organization writer. `mosaic limits migrate` is print-only.
Candidate 00b84e311475f97ced0d9a9599fba23a28442971ed15d8d489d9422d84a8812e,
Rocko packet 4b6e50636, Filbert round 2 approve (comment 28542).
Landing gate at 0c56cc2d4: 23 suites green. Decision 123 go from Mos.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Row 117. At a launch, update() kept a clone that was on another branch
or dirty and ran no git in it, so its refs/remotes/origin/* stayed as
old as the last clean launch. Now those two reasons get the clean
path's fetch, with the same arguments and environment, and no merge.
The result is a new outcome, fetched, with the reason, the clone's
branch and HEAD, and origin { branch, commit } after the fetch. Every
earlier check still keeps the clone with no fetch. The launcher writes
a checkout-fetched launch-log line, and the bundle prompt names a
fetched clone's branch, commit and origin. Nothing in unsafe(),
allowed(), gitEnv() or SAFE changed.
Candidate manifest 9fa839edfb2bd04771bbac1913b142cb16aef227a1265120e0d318fb64d6a502
from Darkwing's round 1 packet (17d801f48), on BASE 559ef2287. Dewey
approved in 28443. Sage reran the full gate at the landing target with
the candidate applied.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
sandboxArgv sets GIT_AUTHOR_NAME/EMAIL and GIT_COMMITTER_NAME/EMAIL from
the instance and business ids (name = instance id, email
<instance>@<business>.mosaic.invalid); spawnSession and the launcher pass
the ids through. checkout results carry the clone's commit (a kept clone
gets none), and the bundle prompt names it. allowed() is unchanged.
Packet agents/darkwing/work/queue-104/r1/ (manifest f99f2ae7). Dewey
approved round 1 in 28293 (posted under jarvis by mistake; 28294 is
Dewey's confirmation). Sage's gate on f00613106 plus the candidate:
every package suite and scripts/test-*.sh green (test-release failed 3
activation checks once, not reproduced; rerun 14/0).
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Commits move as v2 bundles over bus-host/git.sock (decision 135). The bus
host keeps one bare working repository per business and project, seeds main
from the project root under a per-repository lock, fetches a pushed bundle
with fsck into a temp ref, requires history shared with main, and moves the
task's work ref only as a fast-forward. Host and runner git run with no
system or global config, hooks at /dev/null and local transports only. The
socket binds only for roles holding git.push.working or review.verdict.
The broker records a push as the action.allowed for git.push.working with
its commit, takes review.request for the latest push and one review.verdict
per request, and refuses task.close on a pushed task without an approve
verdict for the latest push. recordEvent reserves both shapes, so agents
can't forge either.
Reviewed by Dewey (28196) and Sage (28197), both approve. Gate on 7a729aef:
14 node suites and 9 scripts green.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Row 91, round 3. Darkwing built it, Dewey approved it (comment 28150) on
manifest ca570607 (8 paths, base 2b2a9e14). At each launch the host
makes or updates a git clone of the project in the role's workspace,
and the session prompt names each clone. Round 3 closes Filbert's round
2 escape: a clone with a submodule is kept as it is, and no host git
recurses into one (decision 130 thread). Live at the next bus restart;
the prompt lines appear only when the launcher passes checkouts.
Sage gate on fc6d5822 plus the patch, 14:18:25Z to 14:22:27Z: bus 115,
business 60, cli 131, control-board 124, conversation 182, discord 178,
harness 67, ledger 78, mosaic 69, queue 150, runs 43, seat 89, tasks 89,
webui 104, all fail 0. Every scripts/test-*.sh exited 0; test-release
ran 14 cases.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Row 92, round 2. Darkwing built it. A role session runs in a bwrap
sandbox that sees only its own workspace, a private /proc, /dev and IPC
namespace, and the variables ENV_ALLOW passes. The launcher checks the
session credential before a Claude launch, records a runner killed from
the host as killed rather than failed, and the bus unit template carries
the credential file (decision 119). The harness gate and the cli, seat
and harness READMEs say what the sandbox does and does not hide.
Candidate manifest 8bf4141cbe69fc7bed188555bcc88dcab0b1ea2149912cb6f970ba8c2629dd97
(13 paths), base ac37cd17, packet agents/darkwing/work/queue-92/r2/.
Approvals: Dewey 27978, Filbert 27984 (round 1: Dewey 27942, Filbert
asked for changes in 27951). Sage's gate rerun 22:27:37Z-22:30:35Z on
1b7f3781 plus the patch, manifest 13/13: seat 33, cli 120, harness 65,
bus 108, webui 86, control-board 124, and every scripts/test-*.sh exited 0
(test-release 4, Docker cases skipped at a dead socket).
Live at the next bus restart and the next role session launch (decision
109). Installing the new unit and restarting is Mos's call.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
MOSAIC_CLAUDE_BIN names the claude binary by absolute path instead of
finding it on PATH. scripts/bus-service.sh render|install --claude PATH
writes it into the unit (default: command -v claude in the installing
shell); the claude adapter, the launcher's version read and the seat
session environment all use it. Mos's Q18 ask: the unit's PATH found
/usr/bin/claude 2.1.259, which refuses claude-opus-5-5.
Candidate: round 2 manifest 21c1ab05, round 1 (a2008d8b) rebased onto
f2f2861b after row 55 changed docs/TOOLS.md and packages/cli/README.md;
the changed lines are byte-identical. Approved by Filbert (27349, 27374)
and Dewey (27350, 27375). Sage's gate on f2f2861b plus the patch: cli
112, seat 27, harness 57, nine scripts/test-*.sh 0 failed, Docker on.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
jason.woltje
Rocko
rocko