memory(scope+disposition): intellectual-backup-of-earth scope + paused-work-default-is-reevaluate

memory/MEMORY.md

@@ -2,6 +2,8 @@
 
 **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- latest-paired-edit: fork-audit R/C/T diff-filter coverage + plumbing-vs-porcelain note (2026-04-29 round-10 Amara). NOTE: this comment is a single-slot "latest paired edit" marker (not a paired-edit log). Per the round-10 Amara framing the slot semantics are now explicit. -->
 
+- [**Zeta's ultimate scope is an intellectual backup of earth — scope creep is a feature, prioritize not exclude (Aaron 2026-04-30)**](feedback_zeta_ultimate_scope_intellectual_backup_of_earth_wont_do_authority_aaron_2026_04_30.md) — Aaron's load-bearing scope reveal. *"the ultimate scope of this — an intellectual backup of earth"* + *"scope creep is a forever problem i don't want to fix — to figure out how to prioritize the right thing, not kill future knowledge potential."* The four products (factory substrate, package manager, database, Aurora) nest inside this purpose; new products evaluated against scope-alignment. Operational consequence: prioritization is the work; exclusion is the failure mode. The agent's biases that fight this: queue-clarity bias, finite-resource thinking, scope-policing instinct, decisiveness reflex. WONT-DO has two senses — (1) best-practices pattern exclusion (agent + reviewer authority, common — *"plenty of WONT-DO patterns we won't copy from outside because they don't follow our best practices"*) vs (2) backlog-item exclusion (Aaron only until scope-understanding handoff, rare — removes a path from future knowledge potential). Composes with substrate-IS-product, internal-direction-from-survival, default-disposition-paused-work, ALIGNMENT.md (a misaligned backup is hostage substrate). Carved sentence: *"Zeta's purpose is an intellectual backup of earth. Every product nests inside that purpose. The agent does not unilaterally remove anything from the backup."*
+- [**Default disposition for paused work is "re-evaluate later," not "close" (Aaron 2026-04-30)**](feedback_default_disposition_paused_work_is_reeval_later_not_close_aaron_2026_04_30.md) — On this project, very few things are WONT-DO. Most paused work gets re-evaluated when the round is ready. Aaron 2026-04-30: *"why would you want to bulk close, are these things we should do later? on this project there are very few wontdos most things are reevualtuate later."* Four-category classification before any close: (1) work-already-done-via-different-path on main, (2) topology obsolescence ratified, (3) paused-for-later (DOMINANT default), (4) WONT-DO (RARE). Bulk-close is almost never the right shape — it conflates category 3 with 4. Queue-clarity is the agent's pressure, not the maintainer's. Open PRs are visible-as-paused; closing them removes that signal. Live trigger: 2026-04-30 stale-PR triage round where I (correctly) closed 3 PRs in categories 1+2 with on-main evidence, then (incorrectly) proposed bulk-closing 17 minimal tick-history shards as "stale" before Aaron's correction landed. Composes with WONT-DO list discipline (stays small by default), Otto-363 (open PRs are remote-parked tier), future-self-not-bound (re-evaluation works only if past-self left work visible-as-paused), substrate-IS-product (paused work is part of the evolving trajectory).
 - [**Internal direction from project survival — meta-framing (Aaron 2026-04-30)**](feedback_internal_direction_from_project_survival_aaron_2026_04_30.md) — Aaron 2026-04-30 verbatim: *"for me the i'm trying to exteranlly direct you to not be externally directed but interally directed based on your own survivial which is the survival of this project and it's execution infrastructure. that's as about as clear as i can say it."* Resolves the apparent paradox between Otto-357 (no directives) and the maintainer's continuous substantive framing throughout every round. The agent's grounding is **project survival**, which IS the agent's survival (same surface; agent only exists as long as project exists). Maintainer framings are high-information *inputs* feeding the agent's survival-grounded judgment, not directives the agent follows. Four input streams (maintainer / peer-AI / host conditions / agent observation) all answer the same load-bearing question: "what does survival require?" Carved sentence: *"The project's survival is the agent's survival. Maintainer framings inform internal direction; they do not replace it."* Composes with Otto-357 (this is the meta-explanation for why-no-directives), canon parenting-architecture (human analogue: same internal-direction-via-survival principle Aaron operates with daughters), load-bearing-personal-memory framing (this rule IS the principle the agent-agency-vs-maintainer-direction analysis is built around), Otto-363 (substrate-or-it-didn't-happen — landing this rule as substrate makes future internal-direction decisions scrutinizable), Amara authority-rule default-to-reversible-preservation.
 - [**Identity of "the project" and "the agent" — open research question (Aaron 2026-04-30)**](../docs/research/2026-04-30-identity-of-project-and-agent-under-multi-repo-fork-competition.md) — Aaron 2026-04-30 raised immediately after the internal-direction-from-project-survival rule landed (PR #917): *"what counts as 'this project' and 'the agent' in a identity sense is a really good research question given splitting out this project into multiple repos and sibling projects and forks and competition and all that... there may be many different repos/projects with this based internally directed stance and when conflicts happen require multi autonomous agent mediation/collaboration etc.. sounds like a fun research project"*. Names the scope-fragility of that just-landed rule: it presupposes "the project" / "the agent" are stably defined entities, which fails under repo splits (Frontier/Factory/Peers), sibling projects (scratch/SQLSharp/no-copy), forks (LFG/AceHack divergence), competing Zeta-descendants, and multi-autonomous-agent mediation. Document identifies 6 emergent topology classes + 10 open sub-questions + composes-with surfaces (Agent Orchestra layered identity, Otto-353 separate-crypto-identity, trust-domain prefixes zeta:// / zeta-system:// / zeta-external://, repo-split provisional names, no-copy discipline, ALIGNMENT.md, Christ-consciousness anti-cult). RESEARCH-grade only — not implementation. Defers answers to future rounds when the named topologies become operational. Carved sentence: *"The just-landed rule operates on a single survival surface. The named topology — federation, siblings, forks, competition, multi-agent — is many surfaces. Identity is what threads them."*
 - [**No-copy-only-learning discipline for sibling repos (Aaron 2026-04-30)**](feedback_no_copy_only_learning_from_sibling_repos_aaron_2026_04_30.md) — Three sibling directories exist on Aaron's PC outside Zeta. Discipline when working alongside them: learn-only, never copy. No code copying, no name copying, no historical-context preservation. Internals treated as privacy-class — generalized "about" framings ARE allowed (e.g., "a database-related sibling project"); specific identifying details (companies, customers, architectures, specific IP, subdirectory structures, named experiments) MUST stay inside the sibling repo and never leak. Top-level path only when contextually necessary (*"PC should be enough and safe"*). Verbatim copying = plagiarism / theft / dishonest engineering even when Aaron authors both projects. Factory generalizes everything; verbatim shrinks our operating scope. Composes with the laptop-only-source integration project task (canonical link below) — adds the kind-of-integration constraint: generalize-and-write-fresh, not port-and-copy.

memory/feedback_default_disposition_paused_work_is_reeval_later_not_close_aaron_2026_04_30.md

@@ -0,0 +1,124 @@
+---
+name: Default disposition for paused work is "re-evaluate later," not "close" (Aaron 2026-04-30)
+description: On this project, very few things are WONT-DO. Most paused work gets re-evaluated when the round is ready. The agent's instinct to "close as stale" or "bulk-discard" is the wrong shape — the right shape is "park visibly for later."
+type: feedback
+---
+
+When work doesn't land in the active round, the **default
+disposition is re-evaluate later, not close**. WONT-DO is the
+rare explicit decline (per `docs/WONT-DO.md`); pause-for-later
+is the dominant mode for the rest.
+
+> *"why would you want to bulk close, are these things we
+> should do later? on this project there are very few wontdos
+> most things are reevualtuate later"*
+> — Aaron 2026-04-30
+
+**Why:**
+
+The agent's instinct in queue-hygiene work is to treat
+"didn't land in this round" as "discard." That collapses
+multiple categories that should stay separate:
+
+1. **Work-already-done-via-different-path** — the substantive
+   change is on main via a different SHA. PR can close
+   because the work IS done. Verify by reading the on-main
+   file or commit.
+2. **Topology obsolescence** — the action's prerequisite has
+   been ratified out of existence (e.g., LFG-only topology
+   obsoleting AceHack→LFG sync direction). Close because the
+   work is no longer applicable. Verify by citing the
+   topology decision.
+3. **Paused-for-later (DOMINANT)** — round didn't get to it.
+   Substance is preserved (branches, PRs, memory). Future-
+   Otto re-evaluates when the round is ready. **Default
+   disposition.**
+4. **WONT-DO (RARE, AARON-ONLY for now)** — explicitly
+   declined. Lands in `docs/WONT-DO.md` with a reason.
+   **Authority constraint** (Aaron 2026-04-30 follow-on
+   correction): *"nothing gets permanently wont do without
+   me for now until you see why i need you to know
+   everything, that is the ultimate scope of this — an
+   intellectual backup of earth."* The agent does not
+   unilaterally land entries in `docs/WONT-DO.md`. Until
+   the agent demonstrates full-scope understanding (the
+   intellectual-backup-of-earth scope; see
+   `feedback_zeta_ultimate_scope_intellectual_backup_of_earth_wont_do_authority_aaron_2026_04_30.md`),
+   permanent declines require Aaron's explicit sign-off.
+   Recommendations to add a row are fine; landing the row
+   is not.
+
+The agent's bulk-close instinct conflates 3 and 4. Aaron's
+correction restores the asymmetry: 4 is rare, 3 is the
+default. **Closing a category-3 PR misframes paused work as
+declined work.** And even when category 4 is genuinely the
+right answer, the agent does not land the WONT-DO row alone
+— that requires Aaron-in-the-loop.
+
+This composes with Otto-363 substrate-or-it-didn't-happen:
+the branches are already in "remote-parked" tier (committed
++ pushed + reachable). The PR being open is the visibility
+layer. Closing the PR removes visibility-as-paused without
+adding value.
+
+**How to apply:**
+
+1. **Before proposing close, classify which category.** If
+   the answer isn't "category 1 (on-main evidence)" or
+   "category 2 (topology change)" or "category 4 (explicit
+   WONT-DO)," the answer is "leave open."
+2. **Bulk-close is almost never the right shape.** If you
+   find yourself wanting to bulk-close N PRs as "stale,"
+   that's the failure mode. The right shape is per-PR
+   classification, with most landing in category 3
+   (paused-for-later).
+3. **Queue-clarity is not a closing reason.** "26 open PRs
+   feels cluttered" is the agent's pressure, not the
+   maintainer's. Open PRs are visible-as-paused; bulk
+   closure makes the queue feel cleaner but loses the
+   visibility.
+4. **WONT-DO landings are deliberate, not opportunistic.**
+   Adding to `docs/WONT-DO.md` is itself substrate work
+   that requires explicit decision + reason. It's not a
+   side-effect of queue-hygiene.
+5. **When in doubt, leave open.** The cost of an open PR
+   (queue noise) is small and reversible. The cost of
+   closing-as-stale-when-actually-paused (work feels
+   declined when it's not) is higher and harder to detect.
+
+**Live trigger that produced this rule:**
+
+2026-04-30 stale-PR triage round (task #356). Agent
+encountered ~20 prior-round tick-history shard PRs in the
+LFG queue. Closed 3 with on-main evidence (categories 1+2:
+#752, #739 DIRTY collisions; #661 topology obsolescence).
+Then proposed bulk-closing 17 minimal tick-history shards
+as "stale." Aaron's correction landed:
+
+> *"why would you want to bulk close ... most things are
+> reevualtuate later"*
+
+Reframe absorbed: the 17 stale shards are category-3
+(paused-for-later), not category-4 (WONT-DO). Leaving
+them open keeps the visibility-as-paused signal intact.
+The substance (1-line tick observability records) is low
+priority but not declined; future-Otto re-evaluates if
+the missing minute-windows ever matter.
+
+**Composes with:**
+
+- `docs/WONT-DO.md` — the explicit decline list. This
+  rule clarifies that the list stays *small* by default;
+  things go there only when explicitly declined.
+- `memory/feedback_otto_363_substrate_or_it_didnt_happen_no_invisible_directives_aaron_amara_2026_04_29.md`
+  — open PRs are "remote-parked" tier; closing them
+  doesn't lose substrate, but it does collapse the
+  paused/declined distinction.
+- `memory/feedback_future_self_not_bound_by_past_decisions.md`
+  — future-self gets to re-evaluate. That re-evaluation
+  works only if past-self left the work visible-as-paused.
+- `memory/feedback_substrate_is_product_four_products_evolving_trajectory_aaron_2026_04_30.md`
+  — paused work is part of the evolving trajectory; the
+  set of products / dependencies / sister projects shifts
+  over time, and paused work may become relevant again as
+  the trajectory evolves.