Files

T

mos-dt-0andClaude Opus 5 8cef39f924 docs(remediation): RM-61 MERGED; bank D-43 — I inverted a board fact while compressing to fit the budget

#1033 merged f4fd5967, verified by property: merged=true + merge commit, #1034 (delivery) CLOSED,
#1000 (retirement trigger) still OPEN. The exemption is on main and RM-02 is unblocked.

D-43 is mine. Compressing RM-02's board row to meet the 8KB budget, I turned "2 reviews clear" into
"2 live REQUEST_CHANGES" — an inversion. Provider truth: reviews 63 and 65 are at superseded heads and
live REQUEST_CHANGES at f9746b23 is empty. The real state is subtler than either wording: no live
blocker AND no live approval, because the head carries no review at all.

Caught only by re-deriving RM-02's state from the provider before dispatching, not by re-reading the
board. I was one message from briefing f10-coder to remediate two blocking reviews that do not exist.

The transferable part: this board carries a hard <8KB budget, it exceeded that budget four times in one
session, and each time I shaved prose to fit. Compression IS restatement, and this board's own rule is
"REFERENCE, do not restate" (D-26) because restatement is lossy every time. The budget therefore forces
the exact operation the board forbids, on its most load-bearing table. I flagged that as a risk earlier
in the session; it then materialised as an actual error.

Rule banked: meet a size budget by ROLLING content out to BOARD-LEDGER.md, never by rewording what
stays. Deleting a row and pointing at its authoritative home is safe; paraphrasing to save bytes is not.
Applied immediately — this commit rolls the Decisions-log narrative out verbatim rather than trimming
it, and the board is back under budget at 8096.

And the deeper one, onto RM-34: the orchestrator is the board's sole writer, so nothing external checks
the board against reality. Code has rev-974, gates have the merge-gate, CI has the JSON scan — the
control plane has no independent verifier. Handoff validation must include re-deriving the board's
claims from the provider, not merely confirming a successor can read the file.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>

2026-08-01 09:56:44 -05:00

7.9 KiB

Raw Blame History

mos-remediation — LIVE BOARD (keep < 8 KB)

Phase: EXECUTING — RM-03 at owner-merge; RM-61 MERGED; RM-02 keystone is the front. Updated: 2026-08-01 — seam crossed; successor seat resumed, attested from the files, and is driving. ⚠ That was a MANUAL pane respawn (prior seat ~803k tokens): it validates the checkpoint+rehydration design, NOT a lifecycle mechanism — P-LIFECYCLE rotation does not exist yet (D-41 / RM-62).

Head

Charter + 15 decisions + 4-build plan: MISSION.md. Backlog + all findings: TASKS.md.
Planning DONE (58 tasks, P0–P5). DECISION-1/2/3 all RULED by Mos 2026-07-31 (TASKS.md §5) — nothing is waiting on a decision. D-2's availability target is Jason-pending and non-blocking.
Executing, not planning. RM-01 is MERGED; three lanes are live (see In-flight).
Orchestrator seat mos-remediation LIVE, owns the mission, resumed across the rotation seam 2026-08-01 and re-attested to Mos from the files. Residency attestation: PASS.

In-flight

Task	Owner	State
RM-01 checkout	—	MERGED `f58b3699` (#1027)
RM-03 queue guard	Jason	GO @ `78ec47cd` (cmt 20392) — HELD FOR OWNER MERGE. Head unmoved; GO commit-bound, VOID if it moves — do not push #1032
RM-02 registry ★key	f10-coder	★ UNBLOCKED — now the front. @ `f9746b23`; zero live REQUEST_CHANGES (63/65 superseded) and no live approval either. Next: rebase onto `f4fd5967`, re-CI, review at the new head
RM-61 CI exemption	—	✅ MERGED `f4fd5967` (#1033). #1034 closed; #1000 stays OPEN (retirement trigger). Exemption is on `main`
RM-59 / RM-60	Jason (infra)	tracked deps; RM-60 option B
#1023 queue attempt	Jason	SUPERSEDED-PENDING-JASON — live REQUEST_CHANGES, do not merge

For the incoming orchestrator — read this before acting

RM-02 is the front. RM-03 waits on Jason; RM-61 MERGED; RM-02 needs rebase+CI+review on post-#1033 main. ⚠ Re-derive board claims from the provider before acting (D-43).
docs/remediation/TASKS.md is authoritative, not the newest voice in a chat. It holds 44 findings (D-1…D-6 in BOARD-LEDGER.md, D-7…D-43 + D-38c in TASKS.md), every ruling with its rationale, and the requirements each finding placed on RM-02/RM-34/RM-50/RM-55.
MISSION.md carries five first-class principles, all earned by live failures — observe the property not the proxy · pre-registration prevents retrofitting and nothing else · never ship an integrity claim dressed as a property · when a property cannot exist at its layer, bound it and track the real guarantee · query for refutation, never for confirmation · redundant observation on evidence-bearing steps.
Seat identity: export MOSAIC_GIT_IDENTITY=<seat> is stripped by a context reset (D-34) — every dispatch/rehydration brief must re-export it, or the seat cannot use its credentials.
Scan CI from -f json, never default text — text mode omits clone (D-33). State counts.
The queue guard is zero-information until RM-03 merges (D-23) — never cite its green.
The bounded CI re-roll used on RM-02 was a one-time stopgap, NOT policy. A per-PR free re-roll is D-21 normalisation. Do not repeat it; RM-61 is the fix.

Delivery gates — REFERENCE, do not restate

Canonical: ~/.config/mosaic/fleet/roles.local/merge-gate.md (verdict authority) + ~/.config/mosaic/fleet/roles/validator.md. Order and the freeze/zero-information rules: MISSION.md and KICKSTART.md. Read them there — restating the gate from memory is how the merge-gate step went missing from mission setup twice, once inside the correction for it (D-26).

Fleet seats

mos-remediation — project orchestrator (Claude, /src/mosaic-stack, socket mosaic-fleet) — ACTIVE
planner-opus — adversarial planner (robustness), Opus 5, socket default — DELIVERED, idle
planner-sol — adversarial planner (pragmatic), gpt-5.6-sol, socket default — DELIVERED, idle
rev-974 — mosaicstack reviewer identity (id 16, write:repository) — idle, on call
Mos (mos-claude) — lead coordinator, socket default — relay path to Jason

Gate status

Freeze: LIFTED for this workstream only.
Git identity: orchestrator runs MOSAIC_GIT_IDENTITY=mos-dt-0 INTERIM. Mos ruled gate-16 HOLDS (author≠reviewer is what gate-16 protects; rev-974 reviews, mos-dt-0 never self-reviews). Dedicated identity TRACKED, Mos provisions.
Capability is per-path (D-11b → superseded in part by D-13/D-15): a token file is necessary, not sufficient. Three layers — token file (raw-API), tea login (tea paths), repository permission (writes). Before dispatch, assert permissions.push == true as that seat, not token existence and not a 200 on a read. Mos owns provisioning; escalate missing pairs.
Seat identity (D-11a): token identity AND git config user.name/user.email must BOTH be set and agree. Exporting MOSAIC_GIT_IDENTITY alone does NOT fix commit authorship.
⚠ LIVE HAZARD (D-37) — one shared .git/config re-identifies EVERY worktree at once. Every seat, including rev-974's review worktree, currently authors as coder-mos1; MOSAIC_GIT_IDENTITY does not override it. STANDING ORDER: commit with explicit git -c user.name=<seat> -c user.email=<seat>@…, and NOBODY rewrites the shared config mid-flight. Real fix authorised, Mos owns it, sequenced at a quiet seam. #1024 implicated. Detail: D-37.
Standing worker-brief doctrine (mandatory in EVERY brief): re-export MOSAIC_GIT_IDENTITY (D-34); commit early/WIP (D-31); don't weaken a RED test to pass; if a check is unrunnable SAY SO, never substitute; agent-send -f never -m; artifacts off shared /tmp; scan CI from -f json (D-33); relay observations into an open review, NEVER your own conclusion on an open check (D-39); the author never adjudicates their own PR's blocker status — surface evidence, prepare the fix, hold.
Remote control: native /remote-control NOT wired in this runtime. Path is Mos-relay (Jason ↔ mos-claude via Discord ↔ mos-remediation via agent-send). Not a blocker.

Sequencing — see `MISSION.md`

Builds 1-5, the cross-cutting retirements, and DECISION-1's corrected wire-in target are stated once in the charter and TASKS.md §5. Not repeated here — the previous copy of DECISION-1's status on this board is one of the six stale restatements below.

Decisions log — full record in `TASKS.md`

All 44 findings (D-1…D-6 in BOARD-LEDGER.md, D-7…D-43 + D-38c in TASKS.md) and every ruling with its rationale live there. Not duplicated here. The history of why this board must not restate — six stale copies across two seams — is rolled verbatim into BOARD-LEDGER.md.

7.9 KiB Raw Blame History Unescape Escape