Research addendum: ruling atlas-records-collaborative-work folds Atlas into the sequence (A1 stand-up, A2 collab recall, A3 multi-writer); question atlas-first-writer-set

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/research/2026-10-31-live-mind-sessions-sequence.md

@@ -102,7 +102,14 @@ The operator: "Aqua was gonna work on the notification sounds and ambient sounds
 This binds two things.
 
 - **A brief is closed by its result.** An open self-run follow-up must mean open work, or the goals section (goals-in-turn) is noise and cut 1's inbox would re-tell every stale brief. Owner: the Self actuator. At each `result`, every brief told to the session before or during that turn that her Self has not resolved itself is resolved `Recorded` by the actuator, with the result text (cut on a character boundary at 3800 B, as f2e3805) as the rationale. A longer piece of work she takes on is a follow-up of her own, with a different owner. At session start the same rule is applied to the past: a self-run follow-up claimed by a closed run is resolved `Recorded`, citing that run, whose closure rationale already holds the result. Her Persona then sees results where the brief was, not a pile of open asks. In cut `self-session-live` r2.
-- **Agreements reach the mind of each Mind they bind.** Each Mind writes into her own mind, through memory-write, what she committed to (`committed`), what others agreed to do (`decided`, `about` the other Minds' ids), and the operator's decisions (`decided`, about the operator). A shared plan therefore exists federated, once in each participant's own words, with sources pointing to the same event ids. Whether one mind also holds the plan as a document the others read is question `shared-plan-home`. Where the operator's rulings about a stewarded campaign live is the existing question `ruling-home-for-stewarded-campaigns`. In `persona-memory-write` r3: the `remember` description names agreements between Minds, and the `about` enum takes every sender in the batch, Minds included.
+- **Agreements are recorded in two homes, by scope** (ruling `atlas-records-collaborative-work`, Operator, 2026-10-31: "Just like each steward's own Mind should record and remind them of what work is active in their domain, the shared Atlas Mind should record ongoing collaborative work").
+  - *Her own domain* goes in her own mind, through memory-write: what she was asked, what she committed to, what was decided, what she did. That includes her own part of a shared plan (`committed`, `about` the other Minds' ids).
+  - *Work across Minds* goes in Atlas (`huginn@atlas`): the shared plan, who holds which part, the agreements made between Minds, open items and their state. Every participating Mind's turn is reminded of it. Chat is never the record. Each Atlas document stays owned by its publisher, and only the publisher amends it (`atlas-is-shared-mind-open-evidence`).
+  - The two homes do not compete. Her mind holds her commitment. Atlas holds the plan the commitment belongs to, and her memory cites the Atlas document once it exists.
+  - Facts: `huginn@atlas` is not deployed (unit inactive, no `/etc/gamecult/minds/atlas`). Huginn admission is single-writer: a store is canonical to one instance, and `refuse_foreign_instance` keeps instance-rooted kinds to that instance. The earlier ruling says Huginn owes multi-writer admission.
+  - The interim, until Atlas recall lands: memory-write r3 records her own part and her understanding of the others' parts in her own mind, with sources pointing to the same event ids. Once Atlas lands, the others' parts are no longer hers to record. Her memory keeps only her commitment, which cites the Atlas plan.
+  - Whether Atlas can be stood up with a narrower writer set before full multi-writer admission is question `atlas-first-writer-set`.
+  - Where the operator's rulings about a stewarded campaign live is the existing question `ruling-home-for-stewarded-campaigns`.
 
 ## 2. Cut sequence (revised)
 
@@ -118,8 +125,11 @@ Live first. Memory-write runs beside cut 1 with no shared file.
 | 6 | `persona-session` (merges MAP's `persona-read-tools` r2 and `persona-session`): `mind-persona` holds a leased long-lived claude per conversation, read tools in bwrap, constant schema, chat spooled mid-turn, rotation; unit cap 4 h | Huginn + gamecult-ops | `persona.rs` one connector `TurnRequest` per turn, `MAX_TURNS_PER_START`, the KitConnector transport for Persona turns | after 2 |
 | 7 | `session-keeper`: the heartbeat keeps the floor, writes wakes into live sessions, `live_sessions` vote | Huginn | `heartbeat.rs` `launch()` opening a `PersonaTurn` run per beat | after 6 |
 | 8 | Memory maintenance, ruling home, Cut 12 hand-off (MAP 4, items 2, 6, 7) | Huginn | none | any time |
+| A1 | `atlas-stand-up` (per question `atlas-first-writer-set`): `huginn@atlas` deployed through Idunn and gamecult-ops; admission takes writes from roster Minds, each document rooted at its publisher's instance, which is the caller identity the daemon authenticates (Eyes first: does an admit carry an authenticated caller instance today?); collaboration kinds only (plan, part held by a Mind, agreement, open item) | Huginn + gamecult-ops + Idunn | "a store is canonical to one instance" for Atlas only | 1, 2 |
+| A2 | `atlas-collab-recall`: every participating Mind's Persona turn (and Self start) carries a "Shared work you are in" section read from Atlas; a Persona reply can publish or amend her own Atlas items; memory-write's notes on others' parts are demoted to her own commitment citing the Atlas plan | Huginn | others' parts recorded in her own memory (r3 interim) | after A1, 2 |
+| A3 | Full multi-writer admission: law by rulings and motions, hand-offs, offers and claims, publisher-only amend on every kind (`atlas-is-shared-mind-open-evidence`) | Huginn | the narrow writer set of A1 | after A2 |
 
-Cut 1 alone gives "a session with messages dropping in" for the Self. Cuts 6 and 7 give "at least one active session swarm-wide".
+Cut 1 alone gives "a session with messages dropping in" for the Self. Cuts 6 and 7 give "at least one active session swarm-wide". A1 and A2 give "Atlas records ongoing collaborative work". A1 can run beside cuts 1 and 2 because it shares no file with them (it touches admission's instance rule and deploy, while r3 touches admission's kind tables, which is the one seam to sequence: A1 rebases onto r3).
 
 ## 3. Persistent kinds touched