Lucent-Financial-Group · AceHack · May 27, 2026 · May 27, 2026
diff --git a/...cussions/PR-5047-fix-b-0754-iter-2-empty-systemd-path-broke-clear-nmtui-ping.md b/...cussions/PR-5047-fix-b-0754-iter-2-empty-systemd-path-broke-clear-nmtui-ping.md
@@ -0,0 +1,114 @@
+---
+pr_number: 5047
+title: "fix(B-0754 iter-2): empty systemd PATH broke clear+nmtui+ping+systemctl on real hardware"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:10:32Z"
+merged_at: "2026-05-26T00:22:03Z"
+closed_at: "2026-05-26T00:22:04Z"
+head_ref: "otto-cli/b0754-fix-systemd-path-iter2-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:43Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5047: fix(B-0754 iter-2): empty systemd PATH broke clear+nmtui+ping+systemctl on real hardware
+
+## PR description
+
+## Iteration 1 result (real-hardware test, Aaron 2026-05-25)
+
+Photo evidence on the cluster node screen after booting the v1 ISO:
+
+- `clear: command not found` (line 40 + line 77) — the role-prompt and banner sections
+- `nmtui: command not found` — when ethernet-DHCP wait expired and the wifi-fallback fired
+- Drop-to-shell worked correctly — operator landed at a working root prompt with the recovery hints intact
+
+The substrate-honest failure path validated: the script degraded gracefully and the operator could still complete the install manually (`nmtui` + `zeta-install control-plane` from the recovery shell). But the load-bearing zero-typing-automation flow didn't reach the end. **This PR is the fix so iteration 2 completes unattended.**
+
+## Root cause
+
+NixOS systemd services get a **minimal PATH** by default. The first-boot script's bare commands (`clear`, `nmtui`, `ping`, `systemctl`, plus every command zeta-install.sh would reach for — `lsblk`, `sgdisk`, `mkfs.fat`, `mkfs.ext4`, `mount`, `partprobe`, `partprobe`, etc.) all need either explicit absolute paths OR a configured Environment block on the systemd unit. The interactive-shell PATH that 'just works' for SSH or tty2 login is NOT inherited by Type=idle systemd services.
+
+The reason only `clear` and `nmtui` were observed: `nmtui` blocked first; the rest never executed in the failed path.
+
+## Fix (defense in depth)
+
+### 1. systemd unit Environment block (load-bearing)
+
+`configuration.nix`: explicit `PATH` + `TERM` on the zeta-first-boot service. Covers every current AND future bare command:
+
+```nix
+environment = {
+  PATH = "/run/current-system/sw/bin:/run/current-system/sw/sbin:/run/wrappers/bin";
+  TERM = "linux";
+};
+```
+
+### 2. Script-level belt-and-suspenders
+
+`zeta-first-boot.sh`:
+
+- Replace `clear || true` (×2) with `printf '\\033c' || true` — ANSI 'reset terminal' escape; no external command dependency
+- Change `nmtui` invocation to `/run/current-system/sw/bin/nmtui` (absolute path)
+
+Even if the systemd Environment is overridden by some future change, these two failure modes stay fixed.
+
+## Composes with
+
+- B-0759 first-time-CLI-user persona — drop-to-shell with recovery hints worked exactly as designed; the persona-aligned error path was substrate-honest
+- B-0760 USB-as-repair-tool — same systemd-PATH discipline applies to every command the repair flow will invoke
+- B-0761 reference architecture — this is iteration N of N for the AI-native cluster-bootstrap reference; bandwidth payoff across every future install
+
+## Test plan
+
+- [x] `bash -n` syntax check on edited zeta-first-boot.sh
+- [ ] CI rebuilds ISO via build-ai-cluster-iso.yml (auto-triggers on `full-ai-cluster/usb-nixos-installer/**` path)
+- [ ] Aaron reflashes via zflash + boots cluster node + observes unattended install completes end-to-end
+- [ ] CI green
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-26T00:12:22Z)
+
+## Pull request overview
+
+Fixes the installer ISO’s first-boot automation failing under NixOS systemd’s minimal default `PATH`, so the unattended “zero-typing” flow can complete on real hardware.
+
+**Changes:**
+- Replaced `clear` with an ANSI terminal reset escape to remove reliance on `clear` being in `PATH`.
+- Invoked `nmtui` via an absolute path to avoid `PATH`-inheritance issues.
+- Set explicit `PATH` and `TERM` in the `zeta-first-boot` systemd unit to cover current and future bare command usage in the first-boot flow.
+
+### Reviewed changes
+
+Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
+
+| File | Description |
+| ---- | ----------- |
+| full-ai-cluster/usb-nixos-installer/zeta-first-boot.sh | Removes dependency on `clear` being available and pins `nmtui` to an absolute path for robustness under systemd. |
+| full-ai-cluster/usb-nixos-installer/nixos/installer/configuration.nix | Adds explicit `PATH`/`TERM` to the first-boot systemd unit to ensure all invoked tools are discoverable in the unit environment. |
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-26T00:21:32Z)
+
+## Pull request overview
+
+Copilot reviewed 2 out of 2 changed files in this pull request and generated no new comments.
+
+## Review threads
+
+### Thread 1: full-ai-cluster/usb-nixos-installer/zeta-first-boot.sh:120 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-26T00:12:22Z):
+
+The comment mentions “the env-var below” as a defense, but there isn’t an environment variable being set in the script at/after this point. Consider rewording to reference the systemd unit Environment block (and/or explicitly exporting a PATH in the script if that’s what you meant) so the rationale stays accurate for future readers.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:19:05Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
+
+### @AceHack (2026-05-26T00:19:11Z)
+
+Fixed in `fd160ff1`: reworded the comment to reference the systemd unit's `environment.PATH` override (set in `configuration.nix` on `systemd.services.zeta-first-boot.environment.PATH` via `lib.mkForce`) rather than implying an env-var is set in the shell script. Thanks for the catch.
diff --git a/...ussions/PR-5048-backlog-b-0762-ai-auto-submit-back-telemetry-fixes-from-in-t.md b/...ussions/PR-5048-backlog-b-0762-ai-auto-submit-back-telemetry-fixes-from-in-t.md
@@ -0,0 +1,60 @@
+---
+pr_number: 5048
+title: "backlog(B-0762): AI auto-submit-back telemetry + fixes from in-the-wild installs \u2014 adoption-cost-to-zero flywheel"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:12:34Z"
+merged_at: "2026-05-26T00:14:55Z"
+closed_at: "2026-05-26T00:14:55Z"
+head_ref: "otto-cli/b0762-ai-auto-submit-back-telemetry-flywheel-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:42Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5048: backlog(B-0762): AI auto-submit-back telemetry + fixes from in-the-wild installs — adoption-cost-to-zero flywheel
+
+## PR description
+
+Aaron 2026-05-25 named the adoption-scaling mechanism: each in-the-wild install opt-in submits success/failure telemetry; failures trigger LLM-generated minimal-diff PRs; pattern-matched fixes auto-merge; next operator on similar hardware pays 0 cost. Network-effect substrate; ARC-AGI parallel (B-0761) provides the training data + benchmark catalog. Composes with B-0743 / B-0754-B-0761.
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-26T00:15:24Z)
+
+## Pull request overview
+
+Adds a new P2 backlog row (B-0762) describing an install-time opt-in telemetry loop that can auto-generate minimal-diff fix PRs from in-the-wild failures, aiming to drive “adoption cost → 0” via a network-effect feedback cycle.
+
+**Changes:**
+- Added backlog row **B-0762** capturing the telemetry + auto-fix flywheel concept, acceptance criteria, and privacy/security floor.
+- Updated `docs/BACKLOG.md` index to include **B-0762** under P2.
+
+### Reviewed changes
+
+Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
+
+| File | Description |
+| ---- | ----------- |
+| docs/backlog/P2/B-0762-ai-auto-submit-back-telemetry-fixes-from-in-the-wild-installs-adoption-cost-to-zero-flywheel-aaron-2026-05-25.md | New backlog row defining the telemetry→LLM PR→auto-merge gating loop and acceptance criteria. |
+| docs/BACKLOG.md | Adds B-0762 to the generated backlog index. |
+
+## Review threads
+
+### Thread 1: docs/backlog/P2/B-0762-ai-auto-submit-back-telemetry-fixes-from-in-the-wild-installs-adoption-cost-to-zero-flywheel-aaron-2026-05-25.md:14 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-26T00:15:24Z):
+
+`composes_with` references `B-0743`, but there is no corresponding backlog row (`id: B-0743`) anywhere in the repo. Either add the missing backlog row (or land it in the same PR/stack) or drop this reference to avoid dangling IDs.
+
+### Thread 2: docs/backlog/P2/B-0762-ai-auto-submit-back-telemetry-fixes-from-in-the-wild-installs-adoption-cost-to-zero-flywheel-aaron-2026-05-25.md:19 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-26T00:15:24Z):
+
+`composes_with` includes `B-0758` and `B-0760`, but there are no corresponding backlog rows (`id: B-0758` / `id: B-0760`) in the repo. Add those rows (or update to the correct existing IDs) so backlog cross-references stay resolvable.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:12:38Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-5050-backlog-b-0764-cncf-ecosystem-as-force-multipliers-behind-ze.md b/...ussions/PR-5050-backlog-b-0764-cncf-ecosystem-as-force-multipliers-behind-ze.md
@@ -0,0 +1,27 @@
+---
+pr_number: 5050
+title: "backlog(B-0764): CNCF ecosystem as force multipliers behind Zeta interfaces (KEDA, DAPR, OPA, OAM/KubeVela)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:16:48Z"
+merged_at: "2026-05-26T00:18:54Z"
+closed_at: "2026-05-26T00:18:54Z"
+head_ref: "otto-cli/b0764-cncf-ecosystem-force-multipliers-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:41Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5050: backlog(B-0764): CNCF ecosystem as force multipliers behind Zeta interfaces (KEDA, DAPR, OPA, OAM/KubeVela)
+
+## PR description
+
+Aaron 2026-05-25 named the CNCF-ecosystem-as-force-multipliers pattern: adopt KEDA + DAPR + OPA + OAM/KubeVela + Crossplane + kro + Cilium + Knative + OpenTelemetry + Rook/Ceph as plugins behind Zeta interfaces. Composed via Ace (PM-of-PMs) + ontology negotiation (B-0741). Zeta owns the stable operator contract; CNCF projects ship the substrate underneath; operator gets ecosystem momentum + maintenance distribution for free.
+
+Disambiguates OPA (Open Policy Agent / Rego) vs OAM (Open Application Model). Composes with B-0741 / B-0747 / B-0748 / B-0749 / B-0761 / B-0762 / B-0763.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:16:51Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-5051-backlog-b-0765-p1-servicetitan-route-plug-into-existing-cont.md b/...ussions/PR-5051-backlog-b-0765-p1-servicetitan-route-plug-into-existing-cont.md
@@ -0,0 +1,27 @@
+---
+pr_number: 5051
+title: "backlog(B-0765 P1): ServiceTitan route \u2014 plug into existing control interfaces; ontology negotiation at standards layer"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:20:16Z"
+merged_at: "2026-05-26T00:21:49Z"
+closed_at: "2026-05-26T00:21:49Z"
+head_ref: "otto-cli/b0765-service-titan-route-standards-layer-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:41Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5051: backlog(B-0765 P1): ServiceTitan route — plug into existing control interfaces; ontology negotiation at standards layer
+
+## PR description
+
+Aaron 2026-05-25 named the ServiceTitan strategic principle as substrate-engineering policy: every cluster-install substrate decision filters through 'are we inventing or adopting?'. Prefer adopting existing standards (k8s CRDs, OAM Components, Crossplane Compositions, Helm 3 OCI, ArgoCD, Flux, OpenTelemetry, OPA Rego, DAPR Components, NixOS) over inventing parallel substrate. Sharpens (not retracts) B-0763 + B-0764. Ontology negotiation at the STANDARDS LAYER (not per-project) is the load-bearing leverage point.
+
+P1 because it's the strategic filter shape every future cluster-install row should pass through. Composes with B-0741 / B-0744 / B-0747 / B-0748 / B-0749 / B-0754 / B-0759 / B-0761 / B-0762 / B-0763 / B-0764.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:20:21Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-5053-backlog-b-0767-p1-zeta-native-scheduler-first-dst-ai-aware-c.md b/...ussions/PR-5053-backlog-b-0767-p1-zeta-native-scheduler-first-dst-ai-aware-c.md
@@ -0,0 +1,27 @@
+---
+pr_number: 5053
+title: "backlog(B-0767 P1): Zeta-native scheduler first \u2014 DST + AI-aware cluster management"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:23:39Z"
+merged_at: "2026-05-26T00:25:44Z"
+closed_at: "2026-05-26T00:25:44Z"
+head_ref: "otto-cli/b0767-zeta-native-scheduler-first-dst-ai-aware-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:40Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5053: backlog(B-0767 P1): Zeta-native scheduler first — DST + AI-aware cluster management
+
+## PR description
+
+Aaron 2026-05-25 sequencing call on B-0766 wave order: scheduler is load-bearing enough on (1) DST grounding for the whole cluster + (2) AI-aware scheduling (GPU topology, model locality, workload class, energy cost) that it should be Wave 1, not Wave 2. Binary-compatible via Pod.spec.schedulerName: zeta-scheduler (per B-0765 ServiceTitan route). Sub-waves A-E from baseline through DBSP+Bayesian + multi-objective.
+
+First concrete sub-row of B-0766. Composes with B-0428 (F# fork) + B-0741 / B-0747 / B-0754 / B-0761 / B-0762 / B-0763 / B-0764 / B-0765 / B-0766.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:23:43Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-5055-backlog-b-0769-p1-vc-meta-playbook-control-structure-injecti.md b/...ussions/PR-5055-backlog-b-0769-p1-vc-meta-playbook-control-structure-injecti.md
@@ -0,0 +1,31 @@
+---
+pr_number: 5055
+title: "backlog(B-0769 P1): VC meta-playbook \u2014 control-structure injection around capital flow + adj-EBITDA financial-engineering layer (substrate-honest variant)"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:27:03Z"
+merged_at: "2026-05-26T00:28:52Z"
+closed_at: "2026-05-26T00:28:52Z"
+head_ref: "otto-cli/b0769-vc-meta-playbook-control-structure-injection-substrate-honest-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:39Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5055: backlog(B-0769 P1): VC meta-playbook — control-structure injection around capital flow + adj-EBITDA financial-engineering layer (substrate-honest variant)
+
+## PR description
+
+Aaron 2026-05-25 named the meta-strategy under B-0765 + B-0768: VC meta-playbook (control-structure injection around capital flow in verticals) IS the playbook ServiceTitan executed. Plus sharpening 'with adjusted ebita for specific investor profiles'.
+
+Substrate-honest variant: same control-structure position; opposite value-flow direction. Operator keeps value (open reference per B-0761, vendor-swap per B-0763, opt-in open telemetry per B-0762, binary-compat per B-0766). Failure-mode table + ethical-floor rules guard against extractive drift.
+
+Financial-engineering layer: adjusted EBITDA shaped per investor profile (seed/A → growth equity → pre-IPO → PE → strategic → public markets); substrate-honest variant = TRUE adjustments + single GAAP→non-GAAP bridge + auditor-survivable. ServiceTitan empirical anchor.
+
+Composes with B-0741 / B-0754 / B-0759 / B-0761-B-0768 + 5 ethical-floor rules.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:27:07Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/...ussions/PR-5057-fix-b-0754-iter-3-per-device-partprobe-bare-partprobe-was-hi.md b/...ussions/PR-5057-fix-b-0754-iter-3-per-device-partprobe-bare-partprobe-was-hi.md
@@ -0,0 +1,88 @@
+---
+pr_number: 5057
+title: "fix(B-0754 iter-3): per-device partprobe \u2014 bare partprobe was hitting the boot USB (/dev/sda) + bailing"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-26T00:54:23Z"
+merged_at: "2026-05-26T01:43:12Z"
+closed_at: "2026-05-26T01:43:12Z"
+head_ref: "otto-cli/b0754-iter3-partprobe-per-device-2026-05-25"
+base_ref: "main"
+archived_at: "2026-05-27T19:46:38Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #5057: fix(B-0754 iter-3): per-device partprobe — bare partprobe was hitting the boot USB (/dev/sda) + bailing
+
+## PR description
+
+## Iteration 2 result (cluster node 1, real-hardware test, Aaron 2026-05-25)
+
+Photo evidence on PC 1 shows iter-2 reached 98% of the install path on first try:
+
+- Wifi connected
+- Banner shown
+- Greedy N-disk enum: both Crucial CT1000P3PSSD8 NVMes correctly identified with serials
+- Plan presented (BOOT nvme0n1: ESP 1G + root 256G + longhorn1 rest; DATA nvme1n1: whole disk longhorn2)
+- ZETA_AUTO_CONFIRM=WIPE bypass: WORKED
+- wipefs + sgdisk on both NVMes: SUCCESS
+- GPT partition creation on both NVMes: SUCCESS
+- **Then**: `Error: Partition(s) 1 on /dev/sda have been written, but we have been unable to inform the kernel of the change, probably because it/they are in use`
+- drop_to_shell fired correctly with recovery hints
+
+## Root cause
+
+zeta-install.sh called bare `sudo partprobe` (no args). partprobe with no args probes EVERY block device the kernel knows about. Linux exposes USB mass-storage as `/dev/sda` when no SATA disks present. The booted live ISO has mounted partitions on /dev/sda; partprobe refuses to refresh (rightfully); returns non-zero; `set -euo pipefail` bails.
+
+The greedy N-disk enum ALREADY correctly excluded the USB (TRAN=usb filter). We never partitioned /dev/sda. The partprobe call was the only blanket-all-devices invocation in the whole script.
+
+## Fix
+
+Per-device partprobe on BOOT_DISK + each DATA_DISKS entry. Never blanket. Never touch /dev/sda.
+
+Aaron 2026-05-25: 'i would rather do it right so it's not ambigious for future me / users' — the script now operates on explicit-target devices throughout, no blanket-system-wide invocations remaining.
+
+## Test plan
+
+- [x] `bash -n` syntax check
+- [ ] CI rebuilds ISO via build-ai-cluster-iso.yml
+- [ ] Aaron reflashes via zflash + boots cluster node 1 + observes unattended install reaches end-to-end (cluster member after reboot)
+- [ ] CI green
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-26T00:56:30Z)
+
+## Pull request overview
+
+This PR updates the AI-cluster USB NixOS installer script to avoid calling `partprobe` without arguments (which probes every block device, including the live-boot USB), and instead refreshes the kernel partition table only for the disks that were just partitioned.
+
+**Changes:**
+- Replace blanket `sudo partprobe` with per-device `partprobe` calls for `BOOT_DISK` and each `DATA_DISKS` entry.
+- Add inline rationale documenting why blanket probing is unsafe in this installer context.
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-26T01:11:51Z)
+
+## Pull request overview
+
+Copilot reviewed 2 out of 2 changed files in this pull request and generated no new comments.
+
+## Review threads
+
+### Thread 1: full-ai-cluster/usb-nixos-installer/zeta-install.sh:171 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-26T00:56:29Z):
+
+The comment says the kernel exposes the boot USB as `/dev/sda`, but the assigned `/dev/sdX` letter isn't guaranteed across hardware/boot order. Rewording this to something like “often /dev/sdX (commonly /dev/sda)” would keep the rationale accurate.
+
+### Thread 2: full-ai-cluster/usb-nixos-installer/zeta-install.sh:175 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-26T00:56:30Z):
+
+With `set -euo pipefail`, a `partprobe` failure here will abort the install. Adding an explicit failure handler (e.g., `... || bail "partprobe failed for $disk ..."`) would make the abort message more immediately actionable by identifying the disk and suggesting next steps.
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-26T00:54:27Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).