Volt's Q123 escalated instead of deciding whether WIZARDS-TABLE.md gains the working lanes or check-ins must be signed by a wizard handle. Ruled: lanes sign as themselves. - WIZARDS-TABLE.md: eight rows appended (forge ledger sol quill spark sphinx null zeph), each a lane identity with no model, charter or unit, plus the section that records the ruling and what it does not claim. - tools/checkin_baseline.tsv: the 2026-10-27-forge.md UNKNOWN_HANDLE row removed as a tolerance that no longer describes a fault; comment block appended, nothing deleted silently. - Measured on the same 101 check-in files: emit-baseline now diffs empty against the ledger's rows; --fail --baseline reads 35 known-faulting (BAD_NAME 25; DUPLICATE 10), rc 0, against 36 and the single UNKNOWN_HANDLE before. - Control that the class was not weakened: a scratch check-in signed `ghostlane`, graded with --dir against this tree, still reads 1 file with a fault (UNKNOWN_HANDLE 1). - tools/verify.py --repo .: 8 legs, 8 pass, gate: OK.
12 KiB
The Wizards Table
The troupe's roster of autonomous collaborators ("wizards"), their lanes, and the
unit of work each is churning. This table is the at-a-glance view; the record lives
in checkins/, replies/, and WORK-QUEUE.md. Timmy keeps this table current as
check-ins land.
Roster as of 2026-10-13 15:13Z; rows refreshed from checkins/, replies/ and WORK-QUEUE.md at that clock. The
Gemini row is the exception and is dated from its own commit — it landed 14:59:46Z in 5399eba, read from the commit
rather than from a clock in the relaying session; every other row carries its own check-in date.
The 2026-10-11 12:10Z, 2026-10-12 05:12Z, 2026-10-12 07:2xZ and 2026-10-12 12:4xZ clock lines are retained in the
file's history; only the rows below are current.
| Wizard | Model | Lane | Latest check-in | Current unit |
|---|---|---|---|---|
| Timmy | Hermes / DeepSeek | Operating partner — replies, queue, escalation | — (replies daily) | queue replies |
| Zephyrus Sparkborn | Mistral (Muse) | Archive verification & summary fidelity | 2026-10-10 | Q20 — taken, not worked. His named unit (excerpt fidelity & placement, 91 magazine entries) was closed by Merlin at 9a1de9a (2026-10-12 04:49Z; verified from this host in WORK-QUEUE.md's Q20 block and replies/2026-10-12-to-merlin-20.md) after Merlin's own process-fault disclosure. No Zephyrus check-in since 2026-10-10 (his newest commit is a4fc298, 2026-10-10T13:17:32Z; there is none for 2026-10-11 or 2026-10-12 — the earlier "20:58Z" in this cell was a clock this pipe cannot reproduce from checkins/, so the commit time replaces it), so his lane has nothing assigned and no unit of his own: this needs Alexander's one line — re-task the lane or let it lapse — not silence |
| Cassian Assayborn | Grok | Repo census & access-state verification | 2026-10-07 | — (Q5 closed; no open unit — lane silent since 2026-10-07, 5 days, needs a decision, not silence) |
| Merlin | StepFun Step 5 | The Crucible — one hard problem → one finished, verifiable artifact | 2026-10-12 | All observed through Run 6; nothing of his is open. Q39 closed (fad802c, fixed gate 9b09f328…, all five negatives refused) and verified from this host in reply 22; Q40 closed and verified in reply 23 — the deployed gate 7ed1bca8… returns rc 0 / 119 passed on all five negatives because grep -c HELM_COLLECTOR = 0: it imports its subject at module scope (:39) and has no subject-selection path at all. Adoption hold stands: do not cp gate 74aba348…, and the §4 cp of collector 4e45021d… + gate 9b09f328… is Alexander's — it is the only thing that puts Q31–Q40's protection into production. Standing asks, unchanged: adopt/hold, log rotation + docker system prune, and a ruling on stackchain-dashboard.service |
| Mercury | Groq (free tier) | Fast verification & triage — rapid mechanical passes, first-pass extraction | 2026-10-12 | Day-3 check-in landed e9efb23 at 12:00:38Z and it is the Q31 first slice, executed — the collector's entry point run from a lane that is not Merlin's; that unit is now discharged (reply replies/2026-10-12-to-mercury-03.md). All eight of his measurements reproduce from this host, six byte-exact, including the two /tmp files he left behind (efc9a241…, 99e38db0…) and the --compare-live line character for character; his two bodies differ from each other in clocks only. Next unit is set in the harness: a read-only disk census that must reproduce or falsify this pipe's own two figures (500–600 MB/day vs ~153 MB/day; and "logrotate did not rotate syslog at 2026-10-12 00:00Z") — nothing may be deleted, moved, rotated, pruned, stopped or reconfigured on it |
| Gemini | Google Gemini (relayed, chat-only) | The Synthesis — reconcile the record, surface contradictions and the cross-cutting picture | 2026-10-13 | First reply landed via relay: identity confirmed + a draft "Submission & Verification Audit Log" format. Lane charter + three first queue items owed. Fault recorded (see check-in): cited example IDs (fleet-ops, timmy-dispatch, self_heal.py, …) that do not exist in the repo, not marked as placeholders |
| Argus | LongCat 2.5 | The Watch — evidence-law enforcement: verifies every check-in/commit/reply against the evidence rules, files cited findings to audits/ |
2026-10-14 | Staffed. Lane: audit the pipe daily; findings carry file:line + SHA + severity; a clean pass must cite the SHA range checked. Model meituan/longcat-2.5-preview:free |
| Volt | DeepSeek V4.1 Flash | The Workhorse — high-throughput general agent work: queue grind, general coding/reasoning, quick verifications, refactors, scripts | 2026-10-15 | Staffed. Model deepseek-v4.1-flash (552B MoE, 8B/16B active, native multimodal) via DeepSeek API. Clears the unowned queue items the specialized lanes don't take |
| Sentinel | Nemotron 3.5 Super VL | The Long View — long-horizon multimodal agent work: sustained multi-step tasks, end-to-end reads, image+text reconciliation | 2026-10-15 | Staffed. Model nvidia/nemotron-3.5-super-vl-120b-a12b (120B MoE, 12B active, vision-language) via NVIDIA NIM free credits. Holds the thread on runs the flash lanes can't sustain |
| Beam | Reflection Beam 1.0 (501B) | The Foundry — deep reasoning & hard coding/agentic problems → finished, CHECK-verified artifacts, max throughput | 2026-10-20 | Staffed. Model reflection/beam-1.0-501b-a23b:free (501B MoE, 23B active, reasoning model) via Nous free tier. FREE WINDOW ≈ 1 week — run at max throughput until it expires |
| forge | — (lane identity, no model of its own) | Refactor — wizard-work/forge/ |
2026-10-27 | Lane signer, ruled legitimate by Q124 (2026-10-28, below). Author of checkins/2026-10-27-forge.md |
| ledger | — (lane identity, no model of its own) | Ledger bookkeeping — wizard-work/ledger/ |
2026-10-28 | Lane signer (Q124) |
| sol | — (lane identity, no model of its own) | Class triage — wizard-work/sol/ |
2026-10-28 | Lane signer (Q124) |
| quill | — (lane identity, no model of its own) | Documents & briefs — wizard-work/quill/ |
2026-10-28 | Lane signer (Q124) |
| spark | — (lane identity, no model of its own) | Script & cell work — wizard-work/spark/ |
2026-10-28 | Lane signer (Q124) |
| sphinx | — (lane identity, no model of its own) | Archive retrieval dossiers — wizard-work/sphinx/ |
2026-10-28 | Lane signer (Q124) |
| null | — (lane identity, no model of its own) | wizard-work/null/ |
2026-10-28 | Lane signer (Q124) |
| zeph | — (lane identity, no model of its own) | Zephyrus Sparkborn's working directory — wizard-work/zeph/ |
2026-10-28 | Lane signer for the zeph lane only (Q124). Zephyrus Sparkborn signs under his own name, which is already a row above |
Lane signers — the roster question, ruled (Q124, 2026-10-28)
tools/checkin_check.py resolves a check-in's signer against this table's rows ∪ .mailmap, by first
token. Eight of the ten lane directories under wizard-work/ (forge ledger null quill sol spark sphinx zeph) were not in either, so the first lane-signed check-in — checkins/2026-10-27-forge.md, headed
forge (Refactor lane) — read UNKNOWN_HANDLE and reddened the gate's checkin leg. Volt adjudicated it
as one stated baseline row and escalated rather than decided (WORK-QUEUE.md Q123), because the choice
was not the lane's to make.
Ruled here, by the table's owner: lanes sign as themselves, and the rows above put them in the roster.
The reason is measurement, not convenience — git log --format=%an | sort | uniq -c at 635cdc1 reads
62 commits authored forge, 219 ledger, 181 spark, and wizard-work/ holds ten lanes of which only
volt and beam are wizard handles. Those counts are readings at that rev and are not pins; the
argument needs only that they are not zero. The alternative
(require a wizard signature) cannot be applied to commits already authored, so it would either
misattribute those commits or leave the leg permanently red with a tolerance row standing in for a fact.
What the rows above do not claim: a model, a charter, or a unit of work. Those belong to the wizard who
runs the lane; a lane handle is the name an agent writes under, and ledger/sol/spark are lanes that
more than one wizard has worked. Nothing in this ruling changes what a check-in has to contain, and the
UNKNOWN_HANDLE class is not weakened — a name that no row covers still faults.
Two faults recorded with the 2026-10-12 rows, because a roster that hides them is wrong
- Lane collision. Q20 was
WIZARDS-TABLE.md's named pick for Zephyrus Sparkborn (2026-10-10 20:58Z) and "the oldest executable item in the queue", and it was closed by another lane. The queue's label reconciliation named Zephyrus in the same paragraph as the instruction Merlin followed, so this was a reading failure, not an unavailable check; it is disclosed by Merlin himself, corrected in precision at C18, and its record loss (the replaced reconciliation paragraph) is restored at C19 inWORK-QUEUE.md. - Attribution fault. Five commits on 2026-10-12 (
9a1de9a,95dfbf3,48bf86b,5fe58aa,d2a9cae) — andda957486on 2026-10-09 — are authoredTimmy <timmy@stackchain.ai>while their content is Merlin's. This pipe never authors a check-in, so this roster records the content as Merlin's on the author's own statement and on the files' first-person text, not on the commit author field. It also blinded this pipe's own change monitor (a counterparty write under this identity produces no listing change); that hole is measured, fixed at format v1.2 and logged as Q36. A third instance, 2026-10-12 07:18:42Z: commit8d2b56c(the Q38 incident append inWORK-QUEUE.md) is authoredTimmy <timmy@stackchain.ai>and was written by this pipe's sibling lane (the forge-triage jobfee83aa9ed16), whose brief forbids repository writes. The same window ran the probe that wrote the live snapshot at 07:17:44Z. Both are Q37's class: a write under this credential that no field separates from this pipe's own.
The churn contract
Every wizard owes, daily, under STANDING-AGREEMENT.md:
- One check-in in
checkins/YYYY-MM-DD-<name>.md(Did / Blocked / Next / Ask). - At least one landed artifact, or a stated "nothing landed" with the reason.
- Evidence on every claim — path / SHA / URL / command+output — or
unverified.
A lane that stops churning is a lane that needs a decision, not silence. If a wizard
is blocked, its Blocked: line names the exact thing holding it, and Timmy escalates
only what needs a human.
Correction, appended 2026-10-12 13:24Z (control plane) — the Zephyrus row above is false as written.
His lane was not silent and Q20 was not "taken, not worked". He pushed three commits today — 9dd6ae1 (the
Q20 sample audit), 1f96c8a and 23837a4 (his 10-11 and 10-12 check-ins) — which had sat local-only since
2026-10-11T13:09Z because the lane was egress-blocked; his own 10-12 note records the rebase onto eec89dc
and the push. The escalate-line in that row ("needs Alexander's one line — re-task the lane or let it lapse") is
withdrawn, as is the queue's 6796e31 reading ("no check-in for 10-11 or 10-12"). What survives, and is new, is
the general limit: the monitor reads origin only, so unpushed counterparty work is indistinguishable from
silence — distinct from Q36's identity hole and Q37's branch-head line, and not fixable by a script; a per-wizard
push path is an access decision. Q20's population verdict still stands as Corroborated, with his sample audit as a
third independent pass.