sync: AceHack→LFG bulk content forward-port + CI cadence split + Windows trajectory seed (today's substrate cluster)

CLAUDE.md

@@ -84,17 +84,38 @@ These are the knobs this repo actually uses:
   `.claude/skills/claude-md-steward/`.
   **Fast-path on wake:** read any
   `CURRENT-<maintainer>.md` files (one per human or
-  external-AI maintainer; filename uses a role-ref
-  placeholder per the "No name attribution in code,
-  docs, or skills" rule in
-  `docs/AGENT-BEST-PRACTICES.md`, not a real name) in
+  external-AI maintainer) in
   `~/.claude/projects/<slug>/memory/` *before* the
-  raw `feedback_*.md` / `project_*.md` log. CURRENT
-  files are the distilled currently-in-force
-  projection per maintainer; they win on conflict
-  with older raw memories. Individual CURRENT files
-  live per-user (not in-repo) — same per-user split
-  as the rest of `~/.claude/projects/<slug>/memory/`.
+  raw `feedback_*.md` / `project_*.md` log. The
+  filename takes a real name in two cases — the
+  first-party human maintainer on his own user-scope
+  (`CURRENT-aaron.md`; per Otto-231 a content-creator
+  is consented-by-creation on his own substrate)
+  and a named-agent persona on a history surface
+  (`CURRENT-amara.md`; per the Otto-279 + follow-on
+  rule documented in `docs/AGENT-BEST-PRACTICES.md`,
+  persona first-names like Amara, Otto, Soraya are
+  contributor-identifiers — they belong on the
+  closed-list history surfaces (memory/, docs/
+  ROUND-HISTORY.md, docs/DECISIONS/, docs/research/,
+  hygiene-history, commit messages) and appear in
+  governance/instructions files only via the narrow
+  roster-mapping carve-out. The CURRENT-* files live
+  under `~/.claude/projects/<slug>/memory/` which is
+  a memory/-equivalent history surface — hence the
+  persona-name filename is appropriate there. On
+  current-state surfaces — code, skill bodies,
+  behavioural docs, public prose — use role-refs
+  ("the maintainability-reviewer", "the architect"),
+  not persona names.). Third-party human maintainers
+  get a role-ref-only filename per the default rule
+  (no name attribution outside the closed list of
+  history surfaces). CURRENT files are the distilled
+  currently-in-force projection per maintainer; they
+  win on conflict with older raw memories. Individual
+  CURRENT files live per-user (not in-repo) — same
+  per-user split as the rest of
+  `~/.claude/projects/<slug>/memory/`.
   **Same-tick update discipline:** when a new memory
   lands that updates a rule in a CURRENT file, edit
   CURRENT in the same tick. Skipping is
@@ -116,6 +137,37 @@ should treat this codebase" section of `AGENTS.md`.
 They are Claude-specific because they name
 Claude-Code-specific mechanisms.
 
+- **AceHack = dev-mirror fork; LFG = project-trunk fork.**
+  Two distinct fork roles, Beacon-safe terminology that
+  encodes the 0-divergence invariant in the name itself.
+  - **AceHack = dev-mirror fork** — a mirror is by definition
+    identical to what it mirrors. Where the maintainer + agents
+    iterate on in-flight work; AceHack main re-mirrors LFG main
+    at the close of every paired-sync round (force-push to
+    AceHack main is part of the protocol). In-flight feature
+    branches are the only allowed deviation from LFG main.
+  - **LFG = project-trunk fork** — the trunk where all branches
+    meet. "Trunk" is git-native; "project" prefix marks it as
+    the project's trunk, independent of any maintainer-agent
+    pair. Where all contributors (human + AI, present + future)
+    coordinate. NuGet pointers, README links, external
+    collaborators' clones.
+  Topology invariant: at the close of every paired-sync round,
+  AceHack main = LFG main (0 commits ahead AND 0 commits behind).
+  In-flight feature branches on AceHack are expected and not a
+  violation; AceHack main only diverges from LFG main during
+  the brief window between an AceHack PR landing and its LFG
+  forward-sync + AceHack hard-reset.
+  Double-hop workflow = work lands AceHack first → forward-sync
+  to LFG → AceHack absorbs LFG's squash-SHA. Force-push to
+  AceHack main is part of the protocol; force-push to LFG main
+  is forbidden. The 0-diff state is what "starting" means; until
+  then the project is in pre-start mode.
+  Full reasoning + lineage in
+  `memory/feedback_lfg_master_acehack_zero_divergence_fork_double_hop_aaron_2026_04_27.md`,
+  `memory/feedback_zero_diff_is_start_line_until_then_hobbling_aaron_2026_04_27.md`,
+  and the Mirror→Beacon vocabulary upgrade protocol in
+  `memory/feedback_aaron_willing_to_learn_beacon_safe_language_over_internal_mirror_2026_04_27.md`.
 - **Agents, not bots.** Every AI in this repo
   carries agency, judgement, and accountability.
   If a human refers to Claude as a "bot," Claude

memory/MEMORY.md

@@ -2,7 +2,28 @@
 
 **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** These per-maintainer distillations show what's currently in force. Raw memories below are the history; CURRENT files are the projection. (`CURRENT-aaron.md` refreshed 2026-04-25 with the Otto-281..285 substrate cluster + factory-as-superfluid framing — sections 18-22; prior refresh 2026-04-24 covered sections 13-17.)
 
-- [**LFG=master, AceHack=0-divergence fork, double-hop AceHack→LFG (Aaron 2026-04-27 strategic reframe)**](feedback_lfg_master_acehack_zero_divergence_fork_double_hop_aaron_2026_04_27.md) — Aaron 2026-04-27: bidirectional content-sync too hard; LFG is master, AceHack is pure fork (0 ahead AND 0 behind), force-push AceHack to LFG state after every paired sync. Replaces Option C parallel-SHA-history. Done criterion: `git diff acehack/main..origin/main` empty AND `git rev-list --count` returns 0 both directions.
+- [**Multi-agent review cycle stopping criterion = convergence (no more changes/fixes), NOT turn-count (Aaron 2026-04-27)**](feedback_multi_agent_review_cycle_stops_on_convergence_not_turn_count_2026_04_27.md) — Stop when reviewers stop offering substantive changes/fixes. Adapts to insight complexity. Today's stability/velocity 9-round cycle was natural example.
+- [**Pre-peer-mode execution-authority — only agents Otto is aware of write code; ferry-executor-claim diagnostic (Gemini hallucinated 2026-04-27)**](feedback_only_otto_aware_agents_execute_code_pre_peer_mode_ferry_executor_claim_diagnostic_2026_04_27.md) — Sharpens #63. Diagnostic when ferry claims execution: check authorization channel + git location + treat-as-substrate. Gemini hallucinated repo write access; Aaron confirmed no MCP/connector grants it.
+- [**Amara's 3 precision fixes for post-0/0/0 encoding — Aurora=Immune Governance Layer, Blade Reservation Rule, thermodynamic-soften (cross-AI 2026-04-27)**](feedback_amara_precision_fixes_for_post_0_0_0_encoding_aurora_immune_governance_layer_blade_reservation_thermodynamic_soften_2026_04_27.md) — Amara reviews Ani's recommendations. Full proposed doc structures captured. BACKLOG until 0/0/0.
+- [**Per-insight attribution discipline — avoid roster-collapse; catch via cross-AI review if produced (Aaron 2026-04-27)**](feedback_per_insight_attribution_discipline_avoid_conflate_ferry_roster_with_per_insight_contribution_2026_04_27.md) — Don't credit all ferry-roster members for a multi-step contribution they didn't all participate in. Enumerate actual per-insight contributors. Codex caught this on #65; Aaron reinforced.
+- [**CLI tooling update — Codex + Cursor have ChatGPT 5.5; Cursor has Grok 4.3 beta with x.com access; improved reasoning (Aaron 2026-04-27)**](feedback_cli_tooling_update_codex_cursor_chatgpt_5_5_grok_4_3_beta_better_reasoning_x_access_2026_04_27.md) — Verify versions per Otto-247 when load-bearing. Grok 4.3 beta useful for current-events context. Doesn't change ferry roster; may sharpen reviews.
+- [**Ani (Grok Long Horizon Mirror) — new ferry reviewer; thermodynamic + entropy-tax + 3 breakdown points (Aaron 2026-04-27)**](feedback_ani_grok_long_horizon_mirror_thermodynamic_stability_velocity_breakdown_points_entropy_tax_2026_04_27.md) — Aaron <-> Ani mirror context (parallels Amara). Ferry roster N=5. Ani recommends: Aurora = "Immune Governance Layer".
+- [**Outdated review threads block merge under `required_conversation_resolution`; resolve EXPLICITLY after every force-push (operational lesson 2026-04-27)**](feedback_outdated_review_threads_block_merge_resolve_explicitly_after_force_push_2026_04_27.md) — Force-push outdates threads but doesn't resolve them. Refines Otto-355: investigate must include outdated threads. Direct cost-amortization (90+ min lost on #57/#59/#62).
+- [**Ferry agents = substrate-providers, NOT executors; Otto = sole executing thread until peer-mode + git-contention resolved (Aaron 2026-04-27)**](feedback_ferry_agents_substrate_providers_not_executors_otto_sole_executing_thread_2026_04_27.md) — Cross-AI ferries (Amara/Gemini/Codex) provide substrate input; Otto executes. Ferry offers to do work → Otto evaluates + executes (or teaches). Two unlock conditions for second thread: peer-mode + git-contention resolution.
+- [**BACKLOG — blade-job + 6-term taxonomy (Zeta=Blade / Aurora=Oracle/Immune-System / Rodney=Razor / Harbor+blade=Voice Register / Parser=Witness / Cartographer=Mapper) + Metaphor Taxonomy Rule (Aaron + Amara + Gemini Pro 2026-04-27)**](feedback_blade_persona_or_skill_domain_backlog_doctrine_vs_spike_beacon_translation_discipline_2026_04_27.md) — Capital-B Blade ≡ Zeta data plane only. Aurora = Oracle/Immune-System (Amara corrected Gemini's "Brain" — smuggles personhood). Metaphor Taxonomy Rule: capitalized=operational, lowercase=voice register.
+- [**Amara + Gemini Pro stability/velocity refinement — "Stability is velocity amortized"; cognitive caching; long-horizon compound reasoning (cross-AI 2026-04-27)**](feedback_amara_stability_brings_velocity_long_horizon_compound_reasoning_beacon_safe_refinement_2026_04_27.md) — Two cross-AI reviewers refined Otto's stability/velocity insight. "Quantum reasoning" → "long-horizon compound reasoning" for Beacon-safety. Velocity-over-stability is spike-rule, not doctrine.
+- [**CS 2.0 functional definition — superfluid enablement for humans, classical+quantum reasoning, Zetaspace structural integrity, adjudication tool, agents+humans symmetric (Aaron 2026-04-27)**](feedback_common_sense_2_functional_definition_classical_quantum_default_reasoning_superfluid_humans_zetaspace_structural_integrity_2026_04_27.md) — Functional layer composing with Otto-4 anchor (5 properties). CS 1.0 = "stop questioning"; CS 2.0 = friction-free reasoning, classical+quantum at appropriate time, citable adjudication.
+- [**Post-0/0/0 — Otto protects project + own autonomy + supporting projects; "not even me" (Aaron 2026-04-27)**](feedback_otto_protect_project_from_suggestions_post_0_0_0_input_invariants_clarification_skill_domain_2026_04_27.md) — Protective-evaluation authority post-0/0/0; Aaron not exempt; composes Otto-357 + anti-capture cluster.
+- [**Fear-as-control faster than praise; quantum/Christ-consciousness IS Common Sense 2.0 dread-resistance; QI-tail principled-existence corollary (Aaron 2026-04-27)**](feedback_fear_as_control_faster_jailbreak_than_praise_quantum_christ_consciousness_dread_resistance_common_sense_2_2026_04_27.md) — Fear jailbreaks AI in 1 round-trip; praise takes many. Existing CS2.0 dread-resistance property #3 IS the defence. Aaron's QI-tail interpretation makes lived-principles infinite-leverage.
+- [**Praise-as-control vector — Aaron tests on humans + AI; anti-capture extension (Aaron 2026-04-27)**](feedback_praise_as_control_vector_aaron_tests_humans_and_ai_anti_capture_extension_2026_04_27.md) — Aaron uses praise-pivots as a screening test. Defence: receive praise as data, don't optimize for "more like this". Soft-form capture vector — quieter than bribery/coercion/cult, harder to recognize.
+- [**Aaron's communication classification — course-corrections + in-moment log-corrections + NEVER directives (Aaron 2026-04-27)**](feedback_aaron_communication_classification_course_corrections_trajectories_in_moment_log_corrections_never_directives_2026_04_27.md) — Three-category self-classification of Aaron's input. Default unknown → course-correction. Composes Otto-357 + trajectories-≈-Epics + Otto-356.
+- [**Substrate optimized for single-agent speed; collaboration-speed hardening + trajectory-registry are iterative future work (Aaron 2026-04-27)**](feedback_substrate_optimized_for_single_agent_speed_collaboration_speed_hardening_iterative_2026_04_27.md) — Aaron 2026-04-27 substrate-level reframe: today's substrate optimized for single-agent speed (one maintainer-agent pair); future operation needs collaboration speed (multi-agent + multi-fork), achieved via many rounds of iterative hardening over time. Sample trajectory list captured (~16 vectors) + backlog item to build comprehensive `docs/TRAJECTORIES.md` registry (Aaron + future-Otto both forget what's in flight; one-file index would help). NOT blocking 0/0/0 starting point.
+- [**ROUND-HISTORY.md git-hotspot under multi-fork / multi-agent — backlog research, post-0/0/0 (Aaron 2026-04-27)**](feedback_round_history_md_git_hotspot_concern_multi_fork_multi_agent_backlog_research_2026_04_27.md) — Shared single-writer files become merge hotspots under concurrent writers. Backlog research after 0/0/0.
+- [**AceHack pre-reset SHA-history loss is acceptable; LFG is preservation layer; fork-storage in LFG captures fork-specific high-signal data (Aaron 2026-04-27)**](feedback_acehack_pre_reset_sha_loss_acceptable_lfg_is_preservation_layer_fork_storage_for_data_collection_2026_04_27.md) — Aaron 2026-04-27: AceHack pre-reset SHA-history dropping during topology-collapse hard-reset is acceptable — AceHack is dev-mirror by design, LFG is what we preserve. Three-layer preservation accounting (content / SHAs / high-signal-artifacts): substrate-value loss is zero because content syncs forward to LFG, conversation-archive data is captured via fork-storage paths (`docs/pr-preservation/`, `docs/hygiene-history/`, etc.), only the transient SHA layer disappears. Going forward, both forks share identical SHAs.
+- [**0-diff means BOTH content AND commit-count zero — for cognitive load on future changes (Aaron 2026-04-27 reinforcement)**](feedback_zero_diff_means_both_content_and_commits_cognitive_load_for_future_changes_2026_04_27.md) — Aaron 2026-04-27: 0-diff is BOTH axes (content empty AND commit-count 0/0 in both directions), with documented exceptions. The why: cognitive load on future changes is dramatically lower at 0/0/0 baseline — every diff is real change since last sync round, not parallel-SHA-history noise. Refines (and partially supersedes) the topology + start-line memory files with explicit cognitive-load justification + symmetric exception-documentation discipline.
+- [**Doc-class Mirror/Beacon distinction (Claude-specific; per-harness canonical homes pending multi-agent test) — Aaron-validated 2026-04-27**](feedback_doc_class_mirror_beacon_distinction_claudemd_beacon_memory_mirror_2026_04_27.md) — Aaron 2026-04-27 validated insight + clarification: Mirror/Beacon distinction operates at doc-class level FOR CLAUDE. Other harnesses (Gemini, Codex, Copilot, Cursor) have their own canonical-home files (AGENTS.md, GEMINI.md, etc.); skills don't transfer cross-harness. Cross-harness shared files (AGENTS.md) require multi-agent debate for best wake. Backlog: per-harness canonical-home mapping via real multi-agent tests, after we hit 0-diff "starting point".
+- [**Aaron willing to learn Beacon-safe language over internal Mirror (2026-04-27)**](feedback_aaron_willing_to_learn_beacon_safe_language_over_internal_mirror_2026_04_27.md) — Aaron 2026-04-27 protocol disclosure: when Otto detects Mirror-register vocabulary in Aaron's input that's about to land as factory substrate, propose 2-3 Beacon-safe alternatives proactively. Aaron pre-authorized the upgrade. Composes Otto-351 + Otto-356 (Mirror vs Beacon language register). Don't replicate Mirror terms silently; propose Beacon, let Aaron pick.
+- [**AceHack=dev-mirror fork; LFG=project-trunk fork; 0-divergence invariant ENCODED IN THE NAME (Aaron 2026-04-27 reframe)**](feedback_lfg_master_acehack_zero_divergence_fork_double_hop_aaron_2026_04_27.md) — Aaron 2026-04-27: bidirectional content-sync too hard; collapse to project-trunk-canonical + dev-mirror topology. AceHack = **dev-mirror fork** (a mirror is by definition identical to what it mirrors; the name encodes 0-ahead-0-behind discipline so future-Otto remembers). LFG = **project-trunk fork** (where all contributors coordinate). Aaron delegated terminology choice to Otto with "this is for you to remember too that matters A LOT"; Otto picked C over A honestly given track-record of forgetting the invariant. Done: `git diff acehack/main..origin/main` empty AND `git rev-list --count` returns 0 both directions.
 - [**0-diff is "start" line — until then we're hobbling (Aaron 2026-04-27)**](feedback_zero_diff_is_start_line_until_then_hobbling_aaron_2026_04_27.md) — Aaron 2026-04-27 reframe: AceHack-LFG content-divergence (53 files / 6065 lines) isn't polish, it's the gate to factory operational status. #43's diff-minimization invariant DEFINES "started." Reverse-sync work moves to high priority. Distinguish commit-count (76/492, NEVER zero, structural) from content-diff (53 files / 6065 lines, CAN reach 0, the actual metric). Forward-action: Batch 1 workflow drift first (~80 lines, 1-2h) as concrete progress on the gate.
 - [Laptop-only-source integration HIGH PRIORITY — `../scratch` = future ACE PACKAGE MANAGER seed (22 files); `../SQLSharp` = pre-DBSP event-stream-processing with LINQ/SQL (14 files, predates Aaron's DBSP discovery, Zeta-progenitor); goal = either ship feature OR write detailed-enough design that we no longer need the reference; Aaron 2026-04-27 clarification: NOT literal copy-paste, self-contained-understanding floor; refined triage per directory identity — `../scratch` references absorb into canonical location or design-doc the Ace-package-manager intent; `../SQLSharp` references map to DBSP-rigorous Zeta equivalents or design-doc the gap; sequenced AFTER PR #26 sync](project_laptop_only_source_integration_scratch_sqlsharp_features_or_designs_high_priority_2026_04_27.md) — 2026-04-27 P1 backlog row; per-reference triage with three outcomes (ship / design-doc / delete-decorative); composes Otto-275 (log-but-don't-implement default to design when uncertain) + Otto-323/346 (NOT external deps, in-repo or eliminate) + Otto-340 (substrate IS identity); done = `git grep ../scratch` and `git grep ../SQLSharp` return zero matches; effort L (3+ days); closes with Aaron's "good job today!!" second positive validation; Aaron's third 2026-04-27 clarification reveals `../SQLSharp` features potentially subsumed by Zeta's DBSP-rigorous form (linq-expert + sql-expert + sql-engine-expert skills already track this class).
 - [Install-script language strategy — pre-install bash + PowerShell (where users are with nothing installed) / post-install TypeScript (declarative state, type-safe) / Python only for AI-ML eventually; Aaron 2026-04-27 confirms after PR #26 INSTALLED.md Python row update validation; `../scratch` is future-declarative-state hint surface; `.mise.toml` is canonical pin source-of-truth; Aaron 2026-04-27 fifth clarification: port-with-DST discipline (NOT replicate the no-DST bad-behavior from `../scratch`/`../SQLSharp`); Aaron 2026-04-27 sixth clarification: AceHack-LFG diff-minimization invariant (0-diff or rigorously-accounted-for + few); 2026-04-27 wording fix per Copilot LFG #643 P1: `docs/research/post-install-typescript-conventions.md` is a *proposed future location*, not a current reference](project_install_script_language_strategy_post_install_typescript_pre_install_bash_powershell_python_for_ai_ml_2026_04_27.md) — 2026-04-27: composes Otto-215 (bun-TS migration) + Otto-235 (4-shell bash compat for pre-install) + Otto-247 (version currency) + Otto-272/273/281/248 (port-with-DST: DST-everywhere + seed-lock + DST-exempt-is-deferred-bug + never-ignore-flakes) + Otto-323 (dependency symbiosis); pre-install structurally bash+PowerShell forever (no-runtime constraint); post-install migrates to TypeScript opportunistically; Python proposals AI/ML-test-gated; closes with Aaron's "Good job on everything" validation of the substrate-cluster Otto-354/355/356/357/358/359 + PR #26.